From: Ram Pai linuxram@us.ibm.com

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Signed-off-by: Thiago Jung Bauermann bauerman@linux.ibm.com Acked-by: Ingo Molnar mingo@kernel.org Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + tools/testing/selftests/{x86 => vm}/pkey-helpers.h | 0 tools/testing/selftests/{x86 => vm}/protection_keys.c | 0 tools/testing/selftests/x86/.gitignore | 1 - tools/testing/selftests/x86/Makefile | 2 +- 6 files changed, 3 insertions(+), 2 deletions(-) rename tools/testing/selftests/{x86 => vm}/pkey-helpers.h (100%) rename tools/testing/selftests/{x86 => vm}/protection_keys.c (100%)

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 31b3c98b6d34..c55837bf39fa 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -14,3 +14,4 @@ virtual_address_range gup_benchmark va_128TBswitch map_fixed_noreplace +protection_keys diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 7f9a8a8c31da..4e9c741be6af 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -18,6 +18,7 @@ TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd +TEST_GEN_FILES += protection_keys

ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch diff --git a/tools/testing/selftests/x86/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h similarity index 100% rename from tools/testing/selftests/x86/pkey-helpers.h rename to tools/testing/selftests/vm/pkey-helpers.h diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c similarity index 100% rename from tools/testing/selftests/x86/protection_keys.c rename to tools/testing/selftests/vm/protection_keys.c diff --git a/tools/testing/selftests/x86/.gitignore b/tools/testing/selftests/x86/.gitignore index 7757f73ff9a3..eb30ffd83876 100644 --- a/tools/testing/selftests/x86/.gitignore +++ b/tools/testing/selftests/x86/.gitignore @@ -11,5 +11,4 @@ ldt_gdt iopl mpx-mini-test ioperm -protection_keys test_vdso diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 5d49bfec1e9a..5f16821c7f63 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -12,7 +12,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie)

TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ - protection_keys test_vdso test_vsyscall mov_ss_trap \ + test_vdso test_vsyscall mov_ss_trap \ syscall_arg_fault TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \

From: Ram Pai linuxram@us.ibm.com

This renames PKRU references to "pkey_reg" or "pkey" based on the usage.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Signed-off-by: Thiago Jung Bauermann bauerman@linux.ibm.com Reviewed-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/pkey-helpers.h | 85 +++---- tools/testing/selftests/vm/protection_keys.c | 240 ++++++++++--------- 2 files changed, 170 insertions(+), 155 deletions(-)

diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h index 254e5436bdd9..d5779be4793f 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/vm/pkey-helpers.h @@ -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 @@ -53,85 +53,88 @@ 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 __read_pkey_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 _read_pkey_reg(int line) { - unsigned int pkru = __rdpkru(); + unsigned int pkey_reg = __read_pkey_reg();

- dprintf4("rdpkru(line=%d) pkru: %x shadow: %x\n", - line, pkru, shadow_pkru); - assert(pkru == shadow_pkru); + dprintf4("read_pkey_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 read_pkey_reg() _read_pkey_reg(__LINE__)

-static inline void __wrpkru(unsigned int pkru) +static inline void __write_pkey_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__, + __read_pkey_reg(), pkey_reg); asm volatile(".byte 0x0f,0x01,0xef\n\t" : : "a" (eax), "c" (ecx), "d" (edx)); - assert(pkru == __rdpkru()); + assert(pkey_reg == __read_pkey_reg()); }

-static inline void wrpkru(unsigned int pkru) +static inline void write_pkey_reg(unsigned int pkey_reg) { - dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru); + dprintf4("%s() changing %08x to %08x\n", __func__, + __read_pkey_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()); + read_pkey_reg(); + __write_pkey_reg(pkey_reg); + shadow_pkey_reg = pkey_reg; + dprintf4("%s(%08x) pkey_reg: %08x\n", __func__, + pkey_reg, __read_pkey_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 = read_pkey_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", read_pkey_reg()); + write_pkey_reg(pkey_reg); }

static inline void __pkey_write_allow(int pkey, int do_allow_write) { - long pkru = rdpkru(); + long pkey_reg = read_pkey_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()); + write_pkey_reg(pkey_reg); + dprintf4("pkey_reg now: %08x\n", read_pkey_reg()); }

#define PROT_PKEY0 0x10 /* protection key value (bit 0) */ @@ -181,10 +184,10 @@ 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; @@ -195,21 +198,21 @@ 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; }

diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 480995bceefa..2f4ab81c570d 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Tests x86 Memory Protection Keys (see Documentation/core-api/protection-keys.rst) + * Tests Memory Protection Keys (see Documentation/vm/protection-keys.txt) * * There are examples in here of: * * how to set protection keys on memory - * * how to set/clear bits in PKRU (the rights register) - * * how to handle SEGV_PKRU signals and extract pkey-relevant + * * how to set/clear bits in pkey registers (the rights register) + * * how to handle SEGV_PKUERR signals and extract pkey-relevant * information from the siginfo * * Things to add: @@ -48,7 +48,7 @@ int iteration_nr = 1; int test_nr;

-unsigned int shadow_pkru; +unsigned int shadow_pkey_reg;

#define HPAGE_SIZE (1UL<<21) #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) @@ -255,7 +255,7 @@ static char *si_code_str(int si_code) return "UNKNOWN"; }

-int pkru_faults; +int pkey_faults; int last_si_pkey = -1; void signal_handler(int signum, siginfo_t *si, void *vucontext) { @@ -263,16 +263,16 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) int trapno; unsigned long ip; char *fpregs; - u32 *pkru_ptr; + u32 *pkey_reg_ptr; u64 siginfo_pkey; u32 *si_pkey_ptr; - int pkru_offset; + int pkey_reg_offset; fpregset_t fpregset;

dprint_in_signal = 1; dprintf1(">>>>===============SIGSEGV============================\n"); - dprintf1("%s()::%d, pkru: 0x%x shadow: %x\n", __func__, __LINE__, - __rdpkru(), shadow_pkru); + dprintf1("%s()::%d, pkey_reg: 0x%x shadow: %x\n", __func__, __LINE__, + __read_pkey_reg(), shadow_pkey_reg);

trapno = uctxt->uc_mcontext.gregs[REG_TRAPNO]; ip = uctxt->uc_mcontext.gregs[REG_IP_IDX]; @@ -289,19 +289,19 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) */ fpregs += 0x70; #endif - pkru_offset = pkru_xstate_offset(); - pkru_ptr = (void *)(&fpregs[pkru_offset]); + 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 PKRU fault, we *HAVE* to have at least one bit set in + * If we got a PKEY fault, we *HAVE* to have at least one bit set in * here. */ - dprintf1("pkru_xstate_offset: %d\n", pkru_xstate_offset()); + dprintf1("pkey_reg_xstate_offset: %d\n", pkey_reg_xstate_offset()); if (DEBUG_LEVEL > 4) - dump_mem(pkru_ptr - 128, 256); - pkey_assert(*pkru_ptr); + dump_mem(pkey_reg_ptr - 128, 256); + pkey_assert(*pkey_reg_ptr);

if ((si->si_code == SEGV_MAPERR) || (si->si_code == SEGV_ACCERR) || @@ -317,13 +317,16 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) pkey_assert(siginfo_pkey < NR_PKEYS); last_si_pkey = siginfo_pkey;

- dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr); - /* need __rdpkru() version so we do not do shadow_pkru checking */ - dprintf1("signal pkru from pkru: %08x\n", __rdpkru()); + 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 + */ + dprintf1("signal pkey_reg from pkey_reg: %08x\n", __read_pkey_reg()); dprintf1("pkey from siginfo: %jx\n", siginfo_pkey); - *(u64 *)pkru_ptr = 0x00000000; - dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n"); - pkru_faults++; + *(u64 *)pkey_reg_ptr = 0x00000000; + dprintf1("WARNING: set PKEY_REG=0 to allow faulting instruction to continue\n"); + pkey_faults++; dprintf1("<<<<==================================================\n"); dprint_in_signal = 0; } @@ -402,45 +405,47 @@ pid_t fork_lazy_child(void) static u32 hw_pkey_get(int pkey, unsigned long flags) { u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE); - u32 pkru = __rdpkru(); - u32 shifted_pkru; - u32 masked_pkru; + u32 pkey_reg = __read_pkey_reg(); + u32 shifted_pkey_reg; + u32 masked_pkey_reg;

dprintf1("%s(pkey=%d, flags=%lx) = %x / %d\n", __func__, pkey, flags, 0, 0); - dprintf2("%s() raw pkru: %x\n", __func__, pkru); + dprintf2("%s() raw pkey_reg: %x\n", __func__, pkey_reg);

- shifted_pkru = (pkru >> (pkey * PKRU_BITS_PER_PKEY)); - dprintf2("%s() shifted_pkru: %x\n", __func__, shifted_pkru); - masked_pkru = shifted_pkru & mask; - dprintf2("%s() masked pkru: %x\n", __func__, masked_pkru); + shifted_pkey_reg = (pkey_reg >> (pkey * PKEY_BITS_PER_PKEY)); + 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); /* * shift down the relevant bits to the lowest two, then * mask off all the other high bits. */ - return masked_pkru; + return masked_pkey_reg; }

static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags) { u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE); - u32 old_pkru = __rdpkru(); - u32 new_pkru; + u32 old_pkey_reg = __read_pkey_reg(); + u32 new_pkey_reg;

/* make sure that 'rights' only contains the bits we expect: */ assert(!(rights & ~mask));

- /* copy old pkru */ - new_pkru = old_pkru; + /* copy old pkey_reg */ + new_pkey_reg = old_pkey_reg; /* mask out bits from pkey in old value: */ - new_pkru &= ~(mask << (pkey * PKRU_BITS_PER_PKEY)); + new_pkey_reg &= ~(mask << (pkey * PKEY_BITS_PER_PKEY)); /* OR in new bits for pkey: */ - new_pkru |= (rights << (pkey * PKRU_BITS_PER_PKEY)); + new_pkey_reg |= (rights << (pkey * PKEY_BITS_PER_PKEY));

- __wrpkru(new_pkru); + __write_pkey_reg(new_pkey_reg);

- dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x pkru now: %x old_pkru: %x\n", - __func__, pkey, rights, flags, 0, __rdpkru(), old_pkru); + dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x" + " pkey_reg now: %x old_pkey_reg: %x\n", + __func__, pkey, rights, flags, 0, __read_pkey_reg(), + old_pkey_reg); return 0; }

@@ -449,7 +454,7 @@ void pkey_disable_set(int pkey, int flags) unsigned long syscall_flags = 0; int ret; int pkey_rights; - u32 orig_pkru = rdpkru(); + u32 orig_pkey_reg = read_pkey_reg();

dprintf1("START->%s(%d, 0x%x)\n", __func__, pkey, flags); @@ -465,9 +470,9 @@ void pkey_disable_set(int pkey, int flags)

ret = hw_pkey_set(pkey, pkey_rights, syscall_flags); assert(!ret); - /*pkru and flags have the same format */ - shadow_pkru |= flags << (pkey * 2); - dprintf1("%s(%d) shadow: 0x%x\n", __func__, pkey, shadow_pkru); + /* pkey_reg and flags have the same format */ + shadow_pkey_reg |= flags << (pkey * 2); + dprintf1("%s(%d) shadow: 0x%x\n", __func__, pkey, shadow_pkey_reg);

pkey_assert(ret >= 0);

@@ -475,9 +480,9 @@ void pkey_disable_set(int pkey, int flags) dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__, pkey, pkey, pkey_rights);

- dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru()); + dprintf1("%s(%d) pkey_reg: 0x%x\n", __func__, pkey, read_pkey_reg()); if (flags) - pkey_assert(rdpkru() > orig_pkru); + pkey_assert(read_pkey_reg() > orig_pkey_reg); dprintf1("END<---%s(%d, 0x%x)\n", __func__, pkey, flags); } @@ -487,7 +492,7 @@ void pkey_disable_clear(int pkey, int flags) unsigned long syscall_flags = 0; int ret; int pkey_rights = hw_pkey_get(pkey, syscall_flags); - u32 orig_pkru = rdpkru(); + u32 orig_pkey_reg = read_pkey_reg();

pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));

@@ -498,17 +503,16 @@ void pkey_disable_clear(int pkey, int flags) pkey_rights |= flags;

ret = hw_pkey_set(pkey, pkey_rights, 0); - /* pkru and flags have the same format */ - shadow_pkru &= ~(flags << (pkey * 2)); + shadow_pkey_reg &= ~(flags << (pkey * 2)); 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) pkru: 0x%x\n", __func__, pkey, rdpkru()); + dprintf1("%s(%d) pkey_reg: 0x%x\n", __func__, pkey, read_pkey_reg()); if (flags) - assert(rdpkru() > orig_pkru); + assert(read_pkey_reg() > orig_pkey_reg); }

void pkey_write_allow(int pkey) @@ -561,33 +565,38 @@ int alloc_pkey(void) int ret; unsigned long init_val = 0x0;

- dprintf1("alloc_pkey()::%d, pkru: 0x%x shadow: %x\n", - __LINE__, __rdpkru(), shadow_pkru); + dprintf1("%s()::%d, pkey_reg: 0x%x shadow: %x\n", __func__, + __LINE__, __read_pkey_reg(), shadow_pkey_reg); ret = sys_pkey_alloc(0, init_val); /* - * pkey_alloc() sets PKRU, so we need to reflect it in - * shadow_pkru: + * pkey_alloc() sets PKEY register, so we need to reflect it in + * shadow_pkey_reg: */ - dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", - __LINE__, ret, __rdpkru(), shadow_pkru); + dprintf4("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + __func__, __LINE__, ret, __read_pkey_reg(), + shadow_pkey_reg); if (ret) { /* clear both the bits: */ - shadow_pkru &= ~(0x3 << (ret * 2)); - dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", - __LINE__, ret, __rdpkru(), shadow_pkru); + shadow_pkey_reg &= ~(0x3 << (ret * 2)); + dprintf4("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + __func__, + __LINE__, ret, __read_pkey_reg(), + shadow_pkey_reg); /* * move the new state in from init_val - * (remember, we cheated and init_val == pkru format) + * (remember, we cheated and init_val == pkey_reg format) */ - shadow_pkru |= (init_val << (ret * 2)); + shadow_pkey_reg |= (init_val << (ret * 2)); } - dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", - __LINE__, ret, __rdpkru(), shadow_pkru); - dprintf1("alloc_pkey()::%d errno: %d\n", __LINE__, errno); + dprintf4("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + __func__, __LINE__, ret, __read_pkey_reg(), + shadow_pkey_reg); + dprintf1("%s()::%d errno: %d\n", __func__, __LINE__, errno); /* for shadow checking: */ - rdpkru(); - dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", - __LINE__, ret, __rdpkru(), shadow_pkru); + read_pkey_reg(); + dprintf4("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + __func__, __LINE__, ret, __read_pkey_reg(), + shadow_pkey_reg); return ret; }

@@ -638,8 +647,8 @@ int alloc_random_pkey(void) free_ret = sys_pkey_free(alloced_pkeys[i]); pkey_assert(!free_ret); } - dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__, - __LINE__, ret, __rdpkru(), shadow_pkru); + dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", __func__, + __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); return ret; }

@@ -657,11 +666,13 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, if (nr_iterations-- < 0) break;

- dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__, - __LINE__, ret, __rdpkru(), shadow_pkru); + dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + __func__, __LINE__, ret, __read_pkey_reg(), + shadow_pkey_reg); sys_pkey_free(rpkey); - dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__, - __LINE__, ret, __rdpkru(), shadow_pkru); + dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + __func__, __LINE__, ret, __read_pkey_reg(), + shadow_pkey_reg); } pkey_assert(pkey < NR_PKEYS);

@@ -669,8 +680,8 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, dprintf1("mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n", ptr, size, orig_prot, pkey, ret); pkey_assert(!ret); - dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__, - __LINE__, ret, __rdpkru(), shadow_pkru); + dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", __func__, + __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); return ret; }

@@ -752,7 +763,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) void *ptr; int ret;

- rdpkru(); + read_pkey_reg(); dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__, size, prot, pkey); pkey_assert(pkey < NR_PKEYS); @@ -761,7 +772,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey); pkey_assert(!ret); record_pkey_malloc(ptr, size, prot); - rdpkru(); + read_pkey_reg();

dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr); return ptr; @@ -924,14 +935,14 @@ void *malloc_pkey(long size, int prot, u16 pkey) return ret; }

-int last_pkru_faults; +int last_pkey_faults; #define UNKNOWN_PKEY -2 -void expected_pk_fault(int pkey) +void expected_pkey_fault(int pkey) { - dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n", - __func__, last_pkru_faults, pkru_faults); + dprintf2("%s(): last_pkey_faults: %d pkey_faults: %d\n", + __func__, last_pkey_faults, pkey_faults); dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey); - pkey_assert(last_pkru_faults + 1 == pkru_faults); + pkey_assert(last_pkey_faults + 1 == pkey_faults);

/* * For exec-only memory, we do not know the pkey in @@ -941,23 +952,23 @@ void expected_pk_fault(int pkey) pkey_assert(last_si_pkey == pkey);

/* - * The signal handler shold have cleared out PKRU 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 (__rdpkru() != 0) + if (__read_pkey_reg() != 0) pkey_assert(0);

- __wrpkru(shadow_pkru); - dprintf1("%s() set PKRU=%x to restore state after signal nuked it\n", - __func__, shadow_pkru); - last_pkru_faults = pkru_faults; + __write_pkey_reg(shadow_pkey_reg); + dprintf1("%s() set pkey_reg=%x to restore state after signal " + "nuked it\n", __func__, shadow_pkey_reg); + last_pkey_faults = pkey_faults; last_si_pkey = -1; }

-#define do_not_expect_pk_fault(msg) do { \ - if (last_pkru_faults != pkru_faults) \ - dprintf0("unexpected PK fault: %s\n", msg); \ - pkey_assert(last_pkru_faults == pkru_faults); \ +#define do_not_expect_pkey_fault(msg) do { \ + if (last_pkey_faults != pkey_faults) \ + dprintf0("unexpected PKey fault: %s\n", msg); \ + pkey_assert(last_pkey_faults == pkey_faults); \ } while (0)

int test_fds[10] = { -1 }; @@ -1015,25 +1026,25 @@ 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); - rdpkru(); + read_pkey_reg(); pkey_access_deny(pkey); ptr_contents = read_ptr(ptr); dprintf1("*ptr: %d\n", ptr_contents); - expected_pk_fault(pkey); + 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); pkey_write_deny(pkey); *ptr = __LINE__; - expected_pk_fault(pkey); + expected_pkey_fault(pkey); } void test_write_of_access_disabled_region(int *ptr, u16 pkey) { dprintf1("disabling access to PKEY[%02d], doing write\n", pkey); pkey_access_deny(pkey); *ptr = __LINE__; - expected_pk_fault(pkey); + expected_pkey_fault(pkey); } void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) { @@ -1160,9 +1171,10 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) int new_pkey; dprintf1("%s() alloc loop: %d\n", __func__, i); new_pkey = alloc_pkey(); - dprintf4("%s()::%d, err: %d pkru: 0x%x shadow: 0x%x\n", __func__, - __LINE__, err, __rdpkru(), shadow_pkru); - rdpkru(); /* for shadow checking */ + dprintf4("%s()::%d, err: %d pkey_reg: 0x%x shadow: 0x%x\n", + __func__, __LINE__, err, __read_pkey_reg(), + shadow_pkey_reg); + read_pkey_reg(); /* for shadow checking */ 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", @@ -1201,7 +1213,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) for (i = 0; i < nr_allocated_pkeys; i++) { err = sys_pkey_free(allocated_pkeys[i]); pkey_assert(!err); - rdpkru(); /* for shadow checking */ + read_pkey_reg(); /* for shadow checking */ } }

@@ -1287,7 +1299,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey) pkey_assert(ret != -1); /* Now access from the current task, and expect an exception: */ peek_result = read_ptr(ptr); - expected_pk_fault(pkey); + expected_pkey_fault(pkey);

/* * Try to access the NON-pkey-protected "plain_ptr" via ptrace: @@ -1297,7 +1309,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey) pkey_assert(ret != -1); /* Now access from the current task, and expect NO exception: */ peek_result = read_ptr(plain_ptr); - do_not_expect_pk_fault("read plain pointer after ptrace"); + do_not_expect_pkey_fault("read plain pointer after ptrace");

ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0); pkey_assert(ret != -1); @@ -1347,17 +1359,17 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) pkey_assert(!ret); pkey_access_deny(pkey);

- dprintf2("pkru: %x\n", rdpkru()); + dprintf2("pkey_reg: %x\n", read_pkey_reg());

/* * Make sure this is an *instruction* fault */ madvise(p1, PAGE_SIZE, MADV_DONTNEED); lots_o_noops_around_write(&scratch); - do_not_expect_pk_fault("executing on PROT_EXEC memory"); + do_not_expect_pkey_fault("executing on PROT_EXEC memory"); ptr_contents = read_ptr(p1); dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); - expected_pk_fault(pkey); + expected_pkey_fault(pkey); }

void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) @@ -1378,15 +1390,15 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) ret = mprotect(p1, PAGE_SIZE, PROT_EXEC); pkey_assert(!ret);

- dprintf2("pkru: %x\n", rdpkru()); + dprintf2("pkru: %x\n", read_pkey_reg());

/* Make sure this is an *instruction* fault */ madvise(p1, PAGE_SIZE, MADV_DONTNEED); lots_o_noops_around_write(&scratch); - do_not_expect_pk_fault("executing on PROT_EXEC memory"); + do_not_expect_pkey_fault("executing on PROT_EXEC memory"); ptr_contents = read_ptr(p1); dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); - expected_pk_fault(UNKNOWN_PKEY); + expected_pkey_fault(UNKNOWN_PKEY);

/* * Put the memory back to non-PROT_EXEC. Should clear the @@ -1400,7 +1412,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) ret = mprotect(p1, PAGE_SIZE, PROT_READ|PROT_EXEC); pkey_assert(!ret); ptr_contents = read_ptr(p1); - do_not_expect_pk_fault("plain read on recently PROT_EXEC area"); + do_not_expect_pkey_fault("plain read on recently PROT_EXEC area"); }

void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) @@ -1442,7 +1454,7 @@ void run_tests_once(void)

for (test_nr = 0; test_nr < ARRAY_SIZE(pkey_tests); test_nr++) { int pkey; - int orig_pkru_faults = pkru_faults; + int orig_pkey_faults = pkey_faults;

dprintf1("======================\n"); dprintf1("test %d preparing...\n", test_nr); @@ -1457,8 +1469,8 @@ void run_tests_once(void) free_pkey_malloc(ptr); sys_pkey_free(pkey);

- dprintf1("pkru_faults: %d\n", pkru_faults); - dprintf1("orig_pkru_faults: %d\n", orig_pkru_faults); + dprintf1("pkey_faults: %d\n", pkey_faults); + dprintf1("orig_pkey_faults: %d\n", orig_pkey_faults);

tracing_off(); close_test_fds(); @@ -1471,7 +1483,7 @@ void run_tests_once(void)

void pkey_setup_shadow(void) { - shadow_pkru = __rdpkru(); + shadow_pkey_reg = __read_pkey_reg(); }

int main(void) @@ -1495,7 +1507,7 @@ int main(void) }

pkey_setup_shadow(); - printf("startup pkru: %x\n", rdpkru()); + printf("startup pkey_reg: %x\n", read_pkey_reg()); setup_hugetlbfs();

while (nr_iterations-- > 0)

From: Thiago Jung Bauermann bauerman@linux.ibm.com

In preparation for multi-arch support, move definitions which have arch-specific values to x86-specific header.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Signed-off-by: Thiago Jung Bauermann bauerman@linux.ibm.com Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/pkey-helpers.h | 111 +------------ tools/testing/selftests/vm/pkey-x86.h | 156 +++++++++++++++++++ tools/testing/selftests/vm/protection_keys.c | 47 ------ 3 files changed, 162 insertions(+), 152 deletions(-) create mode 100644 tools/testing/selftests/vm/pkey-x86.h

diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h index 6ad1bd54ef94..3ed2f021bf7a 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/vm/pkey-helpers.h @@ -21,9 +21,6 @@

#define PTR_ERR_ENOTSUP ((void *)-ENOTSUP)

-#define NR_PKEYS 16 -#define PKEY_BITS_PER_PKEY 2 - #ifndef DEBUG_LEVEL #define DEBUG_LEVEL 0 #endif @@ -73,19 +70,13 @@ extern void abort_hooks(void); } \ } while (0)

+#if defined(__i386__) || defined(__x86_64__) /* arch */ +#include "pkey-x86.h" +#else /* arch */ +#error Architecture not supported +#endif /* arch */ + extern unsigned int shadow_pkey_reg; -static inline unsigned int __read_pkey_reg(void) -{ - unsigned int eax, edx; - unsigned int ecx = 0; - unsigned int pkey_reg; - - asm volatile(".byte 0x0f,0x01,0xee\n\t" - : "=a" (eax), "=d" (edx) - : "c" (ecx)); - pkey_reg = eax; - return pkey_reg; -}

static inline unsigned int _read_pkey_reg(int line) { @@ -100,19 +91,6 @@ static inline unsigned int _read_pkey_reg(int line)

#define read_pkey_reg() _read_pkey_reg(__LINE__)

-static inline void __write_pkey_reg(unsigned int pkey_reg) -{ - unsigned int eax = pkey_reg; - unsigned int ecx = 0; - unsigned int edx = 0; - - dprintf4("%s() changing %08x to %08x\n", __func__, - __read_pkey_reg(), pkey_reg); - asm volatile(".byte 0x0f,0x01,0xef\n\t" - : : "a" (eax), "c" (ecx), "d" (edx)); - assert(pkey_reg == __read_pkey_reg()); -} - static inline void write_pkey_reg(unsigned int pkey_reg) { dprintf4("%s() changing %08x to %08x\n", __func__, @@ -157,83 +135,6 @@ static inline void __pkey_write_allow(int pkey, int do_allow_write) dprintf4("pkey_reg now: %08x\n", read_pkey_reg()); }

-#define PAGE_SIZE 4096 -#define MB (1<<20) - -static inline void __cpuid(unsigned int *eax, unsigned int *ebx, - unsigned int *ecx, unsigned int *edx) -{ - /* ecx is often an input as well as an output. */ - asm volatile( - "cpuid;" - : "=a" (*eax), - "=b" (*ebx), - "=c" (*ecx), - "=d" (*edx) - : "0" (*eax), "2" (*ecx)); -} - -/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx) */ -#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) -{ - unsigned int eax; - unsigned int ebx; - unsigned int ecx; - unsigned int edx; - - eax = 0x7; - ecx = 0x0; - __cpuid(&eax, &ebx, &ecx, &edx); - - if (!(ecx & X86_FEATURE_PKU)) { - dprintf2("cpu does not have PKU\n"); - return 0; - } - if (!(ecx & X86_FEATURE_OSPKE)) { - dprintf2("cpu does not have OSPKE\n"); - return 0; - } - return 1; -} - -#define XSTATE_PKEY_BIT (9) -#define XSTATE_PKEY 0x200 - -int pkey_reg_xstate_offset(void) -{ - unsigned int eax; - unsigned int ebx; - unsigned int ecx; - unsigned int edx; - int xstate_offset; - int xstate_size; - unsigned long XSTATE_CPUID = 0xd; - int leaf; - - /* 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_PKEY_BIT) { - xstate_offset = ebx; - xstate_size = eax; - } - } - - if (xstate_size == 0) { - printf("could not find size/offset of PKEY in xsave state\n"); - return 0; - } - - return xstate_offset; -} - #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)) diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h new file mode 100644 index 000000000000..2f04ade8ca9c --- /dev/null +++ b/tools/testing/selftests/vm/pkey-x86.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _PKEYS_X86_H +#define _PKEYS_X86_H + +#ifdef __i386__ + +#ifndef SYS_mprotect_key +# define SYS_mprotect_key 380 +#endif + +#ifndef SYS_pkey_alloc +# define SYS_pkey_alloc 381 +# define SYS_pkey_free 382 +#endif + +#define REG_IP_IDX REG_EIP +#define si_pkey_offset 0x14 + +#else + +#ifndef SYS_mprotect_key +# define SYS_mprotect_key 329 +#endif + +#ifndef SYS_pkey_alloc +# define SYS_pkey_alloc 330 +# define SYS_pkey_free 331 +#endif + +#define REG_IP_IDX REG_RIP +#define si_pkey_offset 0x20 + +#endif + +#ifndef PKEY_DISABLE_ACCESS +# define PKEY_DISABLE_ACCESS 0x1 +#endif + +#ifndef PKEY_DISABLE_WRITE +# define PKEY_DISABLE_WRITE 0x2 +#endif + +#define NR_PKEYS 16 +#define PKEY_BITS_PER_PKEY 2 +#define HPAGE_SIZE (1UL<<21) +#define PAGE_SIZE 4096 +#define MB (1<<20) + +static inline void __page_o_noops(void) +{ + /* 8-bytes of instruction * 512 bytes = 1 page */ + asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr"); +} + +static inline unsigned int __read_pkey_reg(void) +{ + unsigned int eax, edx; + unsigned int ecx = 0; + unsigned int pkey_reg; + + asm volatile(".byte 0x0f,0x01,0xee\n\t" + : "=a" (eax), "=d" (edx) + : "c" (ecx)); + pkey_reg = eax; + return pkey_reg; +} + +static inline void __write_pkey_reg(unsigned int pkey_reg) +{ + unsigned int eax = pkey_reg; + unsigned int ecx = 0; + unsigned int edx = 0; + + dprintf4("%s() changing %08x to %08x\n", __func__, + __read_pkey_reg(), pkey_reg); + asm volatile(".byte 0x0f,0x01,0xef\n\t" + : : "a" (eax), "c" (ecx), "d" (edx)); + assert(pkey_reg == __read_pkey_reg()); +} + +static inline void __cpuid(unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile( + "cpuid;" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx) */ +#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) +{ + unsigned int eax; + unsigned int ebx; + unsigned int ecx; + unsigned int edx; + + eax = 0x7; + ecx = 0x0; + __cpuid(&eax, &ebx, &ecx, &edx); + + if (!(ecx & X86_FEATURE_PKU)) { + dprintf2("cpu does not have PKU\n"); + return 0; + } + if (!(ecx & X86_FEATURE_OSPKE)) { + dprintf2("cpu does not have OSPKE\n"); + return 0; + } + return 1; +} + +#define XSTATE_PKEY_BIT (9) +#define XSTATE_PKEY 0x200 + +int pkey_reg_xstate_offset(void) +{ + unsigned int eax; + unsigned int ebx; + unsigned int ecx; + unsigned int edx; + int xstate_offset; + int xstate_size; + unsigned long XSTATE_CPUID = 0xd; + int leaf; + + /* 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_PKEY_BIT) { + xstate_offset = ebx; + xstate_size = eax; + } + } + + if (xstate_size == 0) { + printf("could not find size/offset of PKEY in xsave state\n"); + return 0; + } + + return xstate_offset; +} + +#endif /* _PKEYS_X86_H */ diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 42ffb58810f2..2d0e881f109d 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -49,9 +49,6 @@ int iteration_nr = 1; int test_nr;

unsigned int shadow_pkey_reg; - -#define HPAGE_SIZE (1UL<<21) - int dprint_in_signal; char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];

@@ -137,12 +134,6 @@ void abort_hooks(void) #endif }

-static inline void __page_o_noops(void) -{ - /* 8-bytes of instruction * 512 bytes = 1 page */ - asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr"); -} - /* * This attempts to have roughly a page of instructions followed by a few * instructions that do a write, and another page of instructions. That @@ -165,36 +156,6 @@ void lots_o_noops_around_write(int *write_to_me) dprintf3("%s() done\n", __func__); }

-#ifdef __i386__ - -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 380 -#endif - -#ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 381 -# define SYS_pkey_free 382 -#endif - -#define REG_IP_IDX REG_EIP -#define si_pkey_offset 0x14 - -#else - -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 329 -#endif - -#ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 330 -# define SYS_pkey_free 331 -#endif - -#define REG_IP_IDX REG_RIP -#define si_pkey_offset 0x20 - -#endif - void dump_mem(void *dumpme, int len_bytes) { char *c = (void *)dumpme; @@ -367,14 +328,6 @@ pid_t fork_lazy_child(void) return forkret; }

-#ifndef PKEY_DISABLE_ACCESS -# define PKEY_DISABLE_ACCESS 0x1 -#endif - -#ifndef PKEY_DISABLE_WRITE -# define PKEY_DISABLE_WRITE 0x2 -#endif - static u32 hw_pkey_get(int pkey, unsigned long flags) { u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);

The size of the pkey register can vary across architectures. This converts the data type of all its references to u64 in preparation for multi-arch support.

To keep the definition of the u64 type consistent and remove format specifier related warnings, __SANE_USERSPACE_TYPES__ is defined as suggested by Michael Ellerman.

Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/pkey-helpers.h | 31 +++---- tools/testing/selftests/vm/pkey-x86.h | 8 +- tools/testing/selftests/vm/protection_keys.c | 86 ++++++++++++-------- 3 files changed, 72 insertions(+), 53 deletions(-)

diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h index 7f18a82e54fc..dfbce49269ce 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/vm/pkey-helpers.h @@ -14,10 +14,10 @@ #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 +#define u8 __u8 +#define u16 __u16 +#define u32 __u32 +#define u64 __u64

#define PTR_ERR_ENOTSUP ((void *)-ENOTSUP)

@@ -80,13 +80,14 @@ extern void abort_hooks(void); #error Architecture not supported #endif /* arch */

-extern unsigned int shadow_pkey_reg; +extern u64 shadow_pkey_reg;

-static inline unsigned int _read_pkey_reg(int line) +static inline u64 _read_pkey_reg(int line) { - unsigned int pkey_reg = __read_pkey_reg(); + u64 pkey_reg = __read_pkey_reg();

- dprintf4("read_pkey_reg(line=%d) pkey_reg: %x shadow: %x\n", + dprintf4("read_pkey_reg(line=%d) pkey_reg: %016llx" + " shadow: %016llx\n", line, pkey_reg, shadow_pkey_reg); assert(pkey_reg == shadow_pkey_reg);

@@ -95,15 +96,15 @@ static inline unsigned int _read_pkey_reg(int line)

#define read_pkey_reg() _read_pkey_reg(__LINE__)

-static inline void write_pkey_reg(unsigned int pkey_reg) +static inline void write_pkey_reg(u64 pkey_reg) { - dprintf4("%s() changing %08x to %08x\n", __func__, + dprintf4("%s() changing %016llx to %016llx\n", __func__, __read_pkey_reg(), pkey_reg); /* will do the shadow check for us: */ read_pkey_reg(); __write_pkey_reg(pkey_reg); shadow_pkey_reg = pkey_reg; - dprintf4("%s(%08x) pkey_reg: %08x\n", __func__, + dprintf4("%s(%016llx) pkey_reg: %016llx\n", __func__, pkey_reg, __read_pkey_reg()); }

@@ -113,7 +114,7 @@ static inline void write_pkey_reg(unsigned int pkey_reg) */ static inline void __pkey_access_allow(int pkey, int do_allow) { - unsigned int pkey_reg = read_pkey_reg(); + u64 pkey_reg = read_pkey_reg(); int bit = pkey * 2;

if (do_allow) @@ -121,13 +122,13 @@ static inline void __pkey_access_allow(int pkey, int do_allow) else pkey_reg |= (1<<bit);

- dprintf4("pkey_reg now: %08x\n", read_pkey_reg()); + dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); write_pkey_reg(pkey_reg); }

static inline void __pkey_write_allow(int pkey, int do_allow_write) { - long pkey_reg = read_pkey_reg(); + u64 pkey_reg = read_pkey_reg(); int bit = pkey * 2 + 1;

if (do_allow_write) @@ -136,7 +137,7 @@ static inline void __pkey_write_allow(int pkey, int do_allow_write) pkey_reg |= (1<<bit);

write_pkey_reg(pkey_reg); - dprintf4("pkey_reg now: %08x\n", read_pkey_reg()); + dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); }

#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h index 2f04ade8ca9c..6ffea27e2d2d 100644 --- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/vm/pkey-x86.h @@ -53,11 +53,11 @@ static inline void __page_o_noops(void) asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr"); }

-static inline unsigned int __read_pkey_reg(void) +static inline u64 __read_pkey_reg(void) { unsigned int eax, edx; unsigned int ecx = 0; - unsigned int pkey_reg; + unsigned pkey_reg;

asm volatile(".byte 0x0f,0x01,0xee\n\t" : "=a" (eax), "=d" (edx) @@ -66,13 +66,13 @@ static inline unsigned int __read_pkey_reg(void) return pkey_reg; }

-static inline void __write_pkey_reg(unsigned int pkey_reg) +static inline void __write_pkey_reg(u64 pkey_reg) { unsigned int eax = pkey_reg; unsigned int ecx = 0; unsigned int edx = 0;

- dprintf4("%s() changing %08x to %08x\n", __func__, + dprintf4("%s() changing %016llx to %016llx\n", __func__, __read_pkey_reg(), pkey_reg); asm volatile(".byte 0x0f,0x01,0xef\n\t" : : "a" (eax), "c" (ecx), "d" (edx)); diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 2d0e881f109d..efa35cc6f6b9 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -22,6 +22,7 @@ * gcc -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm */ #define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ #include <errno.h> #include <linux/futex.h> #include <sys/time.h> @@ -48,7 +49,7 @@ int iteration_nr = 1; int test_nr;

-unsigned int shadow_pkey_reg; +u64 shadow_pkey_reg; int dprint_in_signal; char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];

@@ -163,7 +164,7 @@ void dump_mem(void *dumpme, int len_bytes)

for (i = 0; i < len_bytes; i += sizeof(u64)) { u64 *ptr = (u64 *)(c + i); - dprintf1("dump[%03d][@%p]: %016jx\n", i, ptr, *ptr); + dprintf1("dump[%03d][@%p]: %016llx\n", i, ptr, *ptr); } }

@@ -205,7 +206,8 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)

dprint_in_signal = 1; dprintf1(">>>>===============SIGSEGV============================\n"); - dprintf1("%s()::%d, pkey_reg: 0x%x shadow: %x\n", __func__, __LINE__, + dprintf1("%s()::%d, pkey_reg: 0x%016llx shadow: %016llx\n", + __func__, __LINE__, __read_pkey_reg(), shadow_pkey_reg);

trapno = uctxt->uc_mcontext.gregs[REG_TRAPNO]; @@ -213,8 +215,9 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) fpregset = uctxt->uc_mcontext.fpregs; fpregs = (void *)fpregset;

- dprintf2("%s() trapno: %d ip: 0x%lx info->si_code: %s/%d\n", __func__, - trapno, ip, si_code_str(si->si_code), si->si_code); + 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); #ifdef __i386__ /* * 32-bit has some extra padding so that userspace can tell whether @@ -256,8 +259,9 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) * need __read_pkey_reg() version so we do not do shadow_pkey_reg * checking */ - dprintf1("signal pkey_reg from pkey_reg: %08x\n", __read_pkey_reg()); - dprintf1("pkey from siginfo: %jx\n", siginfo_pkey); + dprintf1("signal pkey_reg from pkey_reg: %016llx\n", + __read_pkey_reg()); + dprintf1("pkey from siginfo: %016llx\n", siginfo_pkey); *(u64 *)pkey_reg_ptr = 0x00000000; dprintf1("WARNING: set PKEY_REG=0 to allow faulting instruction to continue\n"); pkey_faults++; @@ -331,16 +335,17 @@ pid_t fork_lazy_child(void) static u32 hw_pkey_get(int pkey, unsigned long flags) { u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE); - u32 pkey_reg = __read_pkey_reg(); - u32 shifted_pkey_reg; + u64 pkey_reg = __read_pkey_reg(); + u64 shifted_pkey_reg; u32 masked_pkey_reg;

dprintf1("%s(pkey=%d, flags=%lx) = %x / %d\n", __func__, pkey, flags, 0, 0); - dprintf2("%s() raw pkey_reg: %x\n", __func__, pkey_reg); + dprintf2("%s() raw pkey_reg: %016llx\n", __func__, pkey_reg);

shifted_pkey_reg = (pkey_reg >> (pkey * PKEY_BITS_PER_PKEY)); - dprintf2("%s() shifted_pkey_reg: %x\n", __func__, shifted_pkey_reg); + dprintf2("%s() shifted_pkey_reg: %016llx\n", __func__, + shifted_pkey_reg); masked_pkey_reg = shifted_pkey_reg & mask; dprintf2("%s() masked pkey_reg: %x\n", __func__, masked_pkey_reg); /* @@ -353,8 +358,8 @@ static u32 hw_pkey_get(int pkey, unsigned long flags) static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags) { u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE); - u32 old_pkey_reg = __read_pkey_reg(); - u32 new_pkey_reg; + u64 old_pkey_reg = __read_pkey_reg(); + u64 new_pkey_reg;

/* make sure that 'rights' only contains the bits we expect: */ assert(!(rights & ~mask)); @@ -369,7 +374,7 @@ static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags) __write_pkey_reg(new_pkey_reg);

dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x" - " pkey_reg now: %x old_pkey_reg: %x\n", + " pkey_reg now: %016llx old_pkey_reg: %016llx\n", __func__, pkey, rights, flags, 0, __read_pkey_reg(), old_pkey_reg); return 0; @@ -380,7 +385,7 @@ void pkey_disable_set(int pkey, int flags) unsigned long syscall_flags = 0; int ret; int pkey_rights; - u32 orig_pkey_reg = read_pkey_reg(); + u64 orig_pkey_reg = read_pkey_reg();

dprintf1("START->%s(%d, 0x%x)\n", __func__, pkey, flags); @@ -390,6 +395,7 @@ void pkey_disable_set(int pkey, int flags)

dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__, pkey, pkey, pkey_rights); + pkey_assert(pkey_rights >= 0);

pkey_rights |= flags; @@ -398,7 +404,8 @@ void pkey_disable_set(int pkey, int flags) assert(!ret); /* pkey_reg and flags have the same format */ shadow_pkey_reg |= flags << (pkey * 2); - dprintf1("%s(%d) shadow: 0x%x\n", __func__, pkey, shadow_pkey_reg); + dprintf1("%s(%d) shadow: 0x%016llx\n", + __func__, pkey, shadow_pkey_reg);

pkey_assert(ret >= 0);

@@ -406,7 +413,8 @@ void pkey_disable_set(int pkey, int flags) dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__, pkey, pkey, pkey_rights);

- dprintf1("%s(%d) pkey_reg: 0x%x\n", __func__, pkey, read_pkey_reg()); + 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__, @@ -418,7 +426,7 @@ void pkey_disable_clear(int pkey, int flags) unsigned long syscall_flags = 0; int ret; int pkey_rights = hw_pkey_get(pkey, syscall_flags); - u32 orig_pkey_reg = read_pkey_reg(); + u64 orig_pkey_reg = read_pkey_reg();

pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));

@@ -436,7 +444,8 @@ void pkey_disable_clear(int pkey, int flags) dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__, pkey, pkey, pkey_rights);

- dprintf1("%s(%d) pkey_reg: 0x%x\n", __func__, pkey, read_pkey_reg()); + dprintf1("%s(%d) pkey_reg: 0x%016llx\n", __func__, + pkey, read_pkey_reg()); if (flags) assert(read_pkey_reg() > orig_pkey_reg); } @@ -491,20 +500,22 @@ int alloc_pkey(void) int ret; unsigned long init_val = 0x0;

- dprintf1("%s()::%d, pkey_reg: 0x%x shadow: %x\n", __func__, - __LINE__, __read_pkey_reg(), shadow_pkey_reg); + dprintf1("%s()::%d, pkey_reg: 0x%016llx shadow: %016llx\n", + __func__, __LINE__, __read_pkey_reg(), shadow_pkey_reg); ret = sys_pkey_alloc(0, init_val); /* * pkey_alloc() sets PKEY register, so we need to reflect it in * shadow_pkey_reg: */ - dprintf4("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); if (ret) { /* clear both the bits: */ shadow_pkey_reg &= ~(0x3 << (ret * 2)); - dprintf4("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); @@ -514,13 +525,15 @@ int alloc_pkey(void) */ shadow_pkey_reg |= (init_val << (ret * 2)); } - dprintf4("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); dprintf1("%s()::%d errno: %d\n", __func__, __LINE__, errno); /* for shadow checking: */ read_pkey_reg(); - dprintf4("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); return ret; @@ -573,7 +586,8 @@ int alloc_random_pkey(void) 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__, + dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); return ret; } @@ -592,11 +606,13 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, if (nr_iterations-- < 0) break;

- dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); sys_pkey_free(rpkey); - dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", + dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); } @@ -606,7 +622,8 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, dprintf1("mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n", ptr, size, orig_prot, pkey, ret); pkey_assert(!ret); - dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", __func__, + dprintf1("%s()::%d, ret: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); return ret; } @@ -885,7 +902,7 @@ void expected_pkey_fault(int pkey) pkey_assert(0);

__write_pkey_reg(shadow_pkey_reg); - dprintf1("%s() set pkey_reg=%x to restore state after signal " + dprintf1("%s() set pkey_reg=%016llx to restore state after signal " "nuked it\n", __func__, shadow_pkey_reg); last_pkey_faults = pkey_faults; last_si_pkey = -1; @@ -1097,7 +1114,8 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) int new_pkey; dprintf1("%s() alloc loop: %d\n", __func__, i); new_pkey = alloc_pkey(); - dprintf4("%s()::%d, err: %d pkey_reg: 0x%x shadow: 0x%x\n", + dprintf4("%s()::%d, err: %d pkey_reg: 0x%016llx" + " shadow: 0x%016llx\n", __func__, __LINE__, err, __read_pkey_reg(), shadow_pkey_reg); read_pkey_reg(); /* for shadow checking */ @@ -1285,7 +1303,7 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) pkey_assert(!ret); pkey_access_deny(pkey);

- dprintf2("pkey_reg: %x\n", read_pkey_reg()); + dprintf2("pkey_reg: %016llx\n", read_pkey_reg());

/* * Make sure this is an *instruction* fault @@ -1316,7 +1334,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) ret = mprotect(p1, PAGE_SIZE, PROT_EXEC); pkey_assert(!ret);

- dprintf2("pkru: %x\n", read_pkey_reg()); + dprintf2("pkey_reg: %016llx\n", read_pkey_reg());

/* Make sure this is an *instruction* fault */ madvise(p1, PAGE_SIZE, MADV_DONTNEED); @@ -1433,7 +1451,7 @@ int main(void) }

pkey_setup_shadow(); - printf("startup pkey_reg: %x\n", read_pkey_reg()); + printf("startup pkey_reg: %016llx\n", read_pkey_reg()); setup_hugetlbfs();

while (nr_iterations-- > 0)

From: Ram Pai linuxram@us.ibm.com

Currently, pkey_disable_clear() sets the specified bits instead clearing them. This has been dead code up to now because its only callers i.e. pkey_access/write_allow() are also unused.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/protection_keys.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index bed9d4de12b4..4b1ddb526228 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -418,7 +418,7 @@ void pkey_disable_clear(int pkey, int flags) pkey, pkey, pkey_rights); pkey_assert(pkey_rights >= 0);

- pkey_rights |= flags; + pkey_rights &= ~flags;

ret = hw_pkey_set(pkey, pkey_rights, 0); shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, pkey, pkey_rights); @@ -431,7 +431,7 @@ void pkey_disable_clear(int pkey, int flags) dprintf1("%s(%d) pkey_reg: 0x%016llx\n", __func__, pkey, read_pkey_reg()); if (flags) - assert(read_pkey_reg() > orig_pkey_reg); + assert(read_pkey_reg() < orig_pkey_reg); }

void pkey_write_allow(int pkey)

From: Ram Pai linuxram@us.ibm.com

alloc_random_pkey() was allocating the same pkey every time. Not all pkeys were geting tested. This fixes it.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/protection_keys.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 7fd52d5c4bfd..9cc82b65f828 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -25,6 +25,7 @@ #define __SANE_USERSPACE_TYPES__ #include <errno.h> #include <linux/futex.h> +#include <time.h> #include <sys/time.h> #include <sys/syscall.h> #include <string.h> @@ -546,10 +547,10 @@ int alloc_random_pkey(void) 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)

From: Ram Pai linuxram@us.ibm.com

This introduces some generic abstractions and provides the corresponding architecture-specfic implementations for these abstractions.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Signed-off-by: Thiago Jung Bauermann bauerman@linux.ibm.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/pkey-helpers.h | 12 ++++++++++++ tools/testing/selftests/vm/pkey-x86.h | 15 +++++++++++++++ tools/testing/selftests/vm/protection_keys.c | 8 ++------ 3 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h index 0e3da7c8d628..621fb2a0a5ef 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/vm/pkey-helpers.h @@ -74,6 +74,9 @@ extern void abort_hooks(void); } \ } while (0)

+__attribute__((noinline)) int read_ptr(int *ptr); +void expected_pkey_fault(int pkey); + #if defined(__i386__) || defined(__x86_64__) /* arch */ #include "pkey-x86.h" #else /* arch */ @@ -172,4 +175,13 @@ static inline void __pkey_write_allow(int pkey, int do_allow_write) #define __stringify_1(x...) #x #define __stringify(x...) __stringify_1(x)

+static inline u32 *siginfo_get_pkey_ptr(siginfo_t *si) +{ +#ifdef si_pkey + return &si->si_pkey; +#else + return (u32 *)(((u8 *)si) + si_pkey_offset); +#endif +} + #endif /* _PKEYS_HELPER_H */ diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h index def2a1bcf6a5..a0c59d4f7af2 100644 --- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/vm/pkey-x86.h @@ -42,6 +42,7 @@ #endif

#define NR_PKEYS 16 +#define NR_RESERVED_PKEYS 2 /* pkey-0 and exec-only-pkey */ #define PKEY_BITS_PER_PKEY 2 #define HPAGE_SIZE (1UL<<21) #define PAGE_SIZE 4096 @@ -158,4 +159,18 @@ int pkey_reg_xstate_offset(void) return xstate_offset; }

+static inline int get_arch_reserved_keys(void) +{ + return NR_RESERVED_PKEYS; +} + +void expect_fault_on_read_execonly_key(void *p1, int pkey) +{ + int ptr_contents; + + ptr_contents = read_ptr(p1); + dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); + expected_pkey_fault(pkey); +} + #endif /* _PKEYS_X86_H */ diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 535e464e27e9..57c71056c93d 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1307,9 +1307,7 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) madvise(p1, PAGE_SIZE, MADV_DONTNEED); lots_o_noops_around_write(&scratch); do_not_expect_pkey_fault("executing on PROT_EXEC memory"); - ptr_contents = read_ptr(p1); - dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); - expected_pkey_fault(pkey); + expect_fault_on_read_execonly_key(p1, pkey); }

void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) @@ -1336,9 +1334,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) madvise(p1, PAGE_SIZE, MADV_DONTNEED); lots_o_noops_around_write(&scratch); do_not_expect_pkey_fault("executing on PROT_EXEC memory"); - ptr_contents = read_ptr(p1); - dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); - expected_pkey_fault(UNKNOWN_PKEY); + expect_fault_on_read_execonly_key(p1, UNKNOWN_PKEY);

/* * Put the memory back to non-PROT_EXEC. Should clear the

From: "Desnes A. Nunes do Rosario" desnesn@linux.vnet.ibm.com

The number of reserved pkeys in a PowerNV environment is different from that on PowerVM or KVM.

Tested on PowerVM and PowerNV environments.

Signed-off-by: "Desnes A. Nunes do Rosario" desnesn@linux.vnet.ibm.com Signed-off-by: Ram Pai linuxram@us.ibm.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/pkey-powerpc.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/vm/pkey-powerpc.h b/tools/testing/selftests/vm/pkey-powerpc.h index c79f4160a6a0..319673bbab0b 100644 --- a/tools/testing/selftests/vm/pkey-powerpc.h +++ b/tools/testing/selftests/vm/pkey-powerpc.h @@ -28,7 +28,10 @@ #define NR_RESERVED_PKEYS_4K 27 /* pkey-0, pkey-1, exec-only-pkey and 24 other keys that cannot be represented in the PTE */ -#define NR_RESERVED_PKEYS_64K 3 /* pkey-0, pkey-1 and exec-only-pkey */ +#define NR_RESERVED_PKEYS_64K_3KEYS 3 /* PowerNV and KVM: pkey-0, + pkey-1 and exec-only key */ +#define NR_RESERVED_PKEYS_64K_4KEYS 4 /* PowerVM: pkey-0, pkey-1, + pkey-31 and exec-only key */ #define PKEY_BITS_PER_PKEY 2 #define HPAGE_SIZE (1UL << 24) #define PAGE_SIZE (1UL << 16) @@ -65,12 +68,27 @@ static inline int cpu_has_pku(void) return 1; }

+static inline bool arch_is_powervm() +{ + struct stat buf; + + if ((stat("/sys/firmware/devicetree/base/ibm,partition-name", &buf) == 0) && + (stat("/sys/firmware/devicetree/base/hmc-managed?", &buf) == 0) && + (stat("/sys/firmware/devicetree/base/chosen/qemu,graphic-width", &buf) == -1) ) + return true; + + return false; +} + static inline int get_arch_reserved_keys(void) { if (sysconf(_SC_PAGESIZE) == 4096) return NR_RESERVED_PKEYS_4K; else - return NR_RESERVED_PKEYS_64K; + if (arch_is_powervm()) + return NR_RESERVED_PKEYS_64K_4KEYS; + else + return NR_RESERVED_PKEYS_64K_3KEYS; }

void expect_fault_on_read_execonly_key(void *p1, int pkey)

From: Ram Pai linuxram@us.ibm.com

For the pkeys subsystem to work, both the CPU and the kernel need to have support. So, additionally check if the kernel supports pkeys apart from the CPU feature checks.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/pkey-helpers.h | 30 ++++++++++++++++++++ tools/testing/selftests/vm/pkey-powerpc.h | 3 +- tools/testing/selftests/vm/pkey-x86.h | 2 +- tools/testing/selftests/vm/protection_keys.c | 7 +++-- 4 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h index 2f4b1eb3a680..59ccdff18214 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/vm/pkey-helpers.h @@ -76,6 +76,8 @@ extern void abort_hooks(void);

__attribute__((noinline)) int read_ptr(int *ptr); void expected_pkey_fault(int pkey); +int sys_pkey_alloc(unsigned long flags, unsigned long init_val); +int sys_pkey_free(unsigned long pkey);

#if defined(__i386__) || defined(__x86_64__) /* arch */ #include "pkey-x86.h" @@ -186,4 +188,32 @@ static inline u32 *siginfo_get_pkey_ptr(siginfo_t *si) #endif }

+static inline int kernel_has_pkeys(void) +{ + /* try allocating a key and see if it succeeds */ + int ret = sys_pkey_alloc(0, 0); + if (ret <= 0) { + return 0; + } + sys_pkey_free(ret); + return 1; +} + +static inline int is_pkeys_supported(void) +{ + /* check if the cpu supports pkeys */ + if (!cpu_has_pkeys()) { + dprintf1("SKIP: %s: no CPU support\n", __func__); + return 0; + } + + /* check if the kernel supports pkeys */ + if (!kernel_has_pkeys()) { + dprintf1("SKIP: %s: no kernel support\n", __func__); + return 0; + } + + return 1; +} + #endif /* _PKEYS_HELPER_H */ diff --git a/tools/testing/selftests/vm/pkey-powerpc.h b/tools/testing/selftests/vm/pkey-powerpc.h index 319673bbab0b..7d7c3ffafdd9 100644 --- a/tools/testing/selftests/vm/pkey-powerpc.h +++ b/tools/testing/selftests/vm/pkey-powerpc.h @@ -63,8 +63,9 @@ static inline void __write_pkey_reg(u64 pkey_reg) __func__, __read_pkey_reg(), pkey_reg); }

-static inline int cpu_has_pku(void) +static inline int cpu_has_pkeys(void) { + /* No simple way to determine this */ return 1; }

diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h index a0c59d4f7af2..6421b846aa16 100644 --- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/vm/pkey-x86.h @@ -97,7 +97,7 @@ 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 int cpu_has_pkeys(void) { unsigned int eax; unsigned int ebx; diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 5fcbbc525364..95f173049f43 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1378,7 +1378,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) int size = PAGE_SIZE; int sret;

- if (cpu_has_pku()) { + if (cpu_has_pkeys()) { dprintf1("SKIP: %s: no CPU support\n", __func__); return; } @@ -1447,12 +1447,13 @@ void pkey_setup_shadow(void) int main(void) { int nr_iterations = 22; + int pkeys_supported = is_pkeys_supported();

setup_handlers();

- printf("has pku: %d\n", cpu_has_pku()); + printf("has pkeys: %d\n", pkeys_supported);

- if (!cpu_has_pku()) { + if (!pkeys_supported) { int size = PAGE_SIZE; int *ptr;

From: Ram Pai linuxram@us.ibm.com

Detect write-violation on a page to which write-disabled key is associated much after the page is mapped.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/protection_keys.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index f65d384ef6a0..cb31a5cdf6d9 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1002,6 +1002,17 @@ 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); @@ -1410,6 +1421,7 @@ void (*pkey_tests[])(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,

From: Ram Pai linuxram@us.ibm.com

This introduces a new allocator that allocates 4K hardware pages to back 64K linux pages. This allocator is available only on powerpc.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Signed-off-by: Thiago Jung Bauermann bauerman@linux.ibm.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/pkey-helpers.h | 6 +++++ tools/testing/selftests/vm/pkey-powerpc.h | 25 ++++++++++++++++++++ tools/testing/selftests/vm/pkey-x86.h | 5 ++++ tools/testing/selftests/vm/protection_keys.c | 1 + 4 files changed, 37 insertions(+)

diff --git a/tools/testing/selftests/vm/pkey-helpers.h b/tools/testing/selftests/vm/pkey-helpers.h index 59ccdff18214..622a85848f61 100644 --- a/tools/testing/selftests/vm/pkey-helpers.h +++ b/tools/testing/selftests/vm/pkey-helpers.h @@ -28,6 +28,9 @@ extern int dprint_in_signal; extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];

+extern int test_nr; +extern int iteration_nr; + #ifdef __GNUC__ __attribute__((format(printf, 1, 2))) #endif @@ -78,6 +81,9 @@ __attribute__((noinline)) int read_ptr(int *ptr); void expected_pkey_fault(int pkey); int sys_pkey_alloc(unsigned long flags, unsigned long init_val); int sys_pkey_free(unsigned long pkey); +int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey); +void record_pkey_malloc(void *ptr, long size, int prot);

#if defined(__i386__) || defined(__x86_64__) /* arch */ #include "pkey-x86.h" diff --git a/tools/testing/selftests/vm/pkey-powerpc.h b/tools/testing/selftests/vm/pkey-powerpc.h index 7d7c3ffafdd9..d31665c48f5e 100644 --- a/tools/testing/selftests/vm/pkey-powerpc.h +++ b/tools/testing/selftests/vm/pkey-powerpc.h @@ -106,4 +106,29 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) /* 4-byte instructions * 16384 = 64K page */ #define __page_o_noops() asm(".rept 16384 ; nop; .endr")

+void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +{ + 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, prot); + + dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr); + return ptr; +} + #endif /* _PKEYS_POWERPC_H */ diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h index 6421b846aa16..3be20f5d5275 100644 --- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/vm/pkey-x86.h @@ -173,4 +173,9 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) expected_pkey_fault(pkey); }

+void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +{ + return PTR_ERR_ENOTSUP; +} + #endif /* _PKEYS_X86_H */ diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 8bb4de103874..d4952b57cc90 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -845,6 +845,7 @@ void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey) 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:

From: Ram Pai linuxram@us.ibm.com

Some platforms hardcode the x86 values for PKEY_DISABLE_ACCESS and PKEY_DISABLE_WRITE such as those in: /usr/include/bits/mman-shared.h.

This overrides the definitions with correct values for powerpc.

cc: Dave Hansen dave.hansen@intel.com cc: Florian Weimer fweimer@redhat.com Signed-off-by: Ram Pai linuxram@us.ibm.com Signed-off-by: Sandipan Das sandipan@linux.ibm.com --- tools/testing/selftests/vm/pkey-powerpc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/vm/pkey-powerpc.h b/tools/testing/selftests/vm/pkey-powerpc.h index d31665c48f5e..02bd4dd7d467 100644 --- a/tools/testing/selftests/vm/pkey-powerpc.h +++ b/tools/testing/selftests/vm/pkey-powerpc.h @@ -16,11 +16,13 @@ #define fpregs fp_regs #define si_pkey_offset 0x20

-#ifndef PKEY_DISABLE_ACCESS +#ifdef PKEY_DISABLE_ACCESS +#undef PKEY_DISABLE_ACCESS # define PKEY_DISABLE_ACCESS 0x3 /* disable read and write */ #endif

-#ifndef PKEY_DISABLE_WRITE +#ifdef PKEY_DISABLE_WRITE +#undef PKEY_DISABLE_WRITE # define PKEY_DISABLE_WRITE 0x2 #endif