[PATCH v2 00/20] Permission Overlay Extension

[PATCH v2 00/20] Permission Overlay Extension

[Joey Gouly]

Hello everyone,

This series implements the Permission Overlay Extension introduced in 2022
VMSA enhancements [1]. It is based on v6.6-rc3.

Changes since v1[2]:
	# Added Kconfig option
	# Added KVM support
	# Move VM_PKEY* defines into arch/
	# Add isb() for POR_EL0 context switch
	# Added hwcap test, get-reg-list-test, signal frame handling test

ptrace support is missing, I will add that for v3.

The Permission Overlay Extension allows to constrain permissions on memory
regions. This can be used from userspace (EL0) without a system call or TLB
invalidation.

POE is used to implement the Memory Protection Keys [3] Linux syscall.

The first few patches add the basic framework, then the PKEYS interface is
implemented, and then the selftests are made to work on arm64.

There was discussion about what the 'default' protection key value should be,
I used disallow-all (apart from pkey 0), which matches what x86 does.

I have tested the modified protection_keys test on x86_64 [5], but not PPC.
I haven't build tested the x86/ppc changes, will work on getting at least
an x86 build environment working.

Thanks,
Joey

[1] https://community.arm.com/arm-community-blogs/b/architectures-and-processors-blog/posts/arm-a-profile-architecture-2022
[2] https://lore.kernel.org/linux-arm-kernel/20230927140123.5283-1-joey.gouly@arm.com/
[3] Documentation/core-api/protection-keys.rst
[4] https://lore.kernel.org/linux-arm-kernel/20230919092850.1940729-7-mark.rutland@arm.com/#t
[5] test_ptrace_modifies_pkru asserts for me on a Ubuntu 5.4 kernel, but does so before my changes as well

Joey Gouly (24):
  arm64/sysreg: add system register POR_EL{0,1}
  arm64/sysreg: update CPACR_EL1 register
  arm64: cpufeature: add Permission Overlay Extension cpucap
  arm64: disable trapping of POR_EL0 to EL2
  arm64: context switch POR_EL0 register
  KVM: arm64: Save/restore POE registers
  arm64: enable the Permission Overlay Extension for EL0
  arm64: add POIndex defines
  arm64: define VM_PKEY_BIT* for arm64
  arm64: mask out POIndex when modifying a PTE
  arm64: enable ARCH_HAS_PKEYS on arm64
  arm64: handle PKEY/POE faults
  arm64: stop using generic mm_hooks.h
  arm64: implement PKEYS support
  arm64: add POE signal support
  arm64: enable PKEY support for CPUs with S1POE
  arm64: enable POE and PIE to coexist
  kselftest/arm64: move get_header()
  selftests: mm: move fpregs printing
  selftests: mm: make protection_keys test work on arm64
  kselftest/arm64: add HWCAP test for FEAT_S1POE
  kselftest/arm64: parse POE_MAGIC in a signal frame
  kselftest/arm64: Add test case for POR_EL0 signal frame records
  KVM: selftests: get-reg-list: add Permission Overlay registers

 Documentation/arch/arm64/elf_hwcaps.rst       |   3 +
 arch/arm64/Kconfig                            |  18 +++
 arch/arm64/include/asm/cpufeature.h           |   6 +
 arch/arm64/include/asm/el2_setup.h            |  10 +-
 arch/arm64/include/asm/hwcap.h                |   1 +
 arch/arm64/include/asm/kvm_arm.h              |   4 +-
 arch/arm64/include/asm/kvm_host.h             |   4 +
 arch/arm64/include/asm/mman.h                 |   8 +-
 arch/arm64/include/asm/mmu.h                  |   2 +
 arch/arm64/include/asm/mmu_context.h          |  51 ++++++-
 arch/arm64/include/asm/page.h                 |  10 ++
 arch/arm64/include/asm/pgtable-hwdef.h        |  10 ++
 arch/arm64/include/asm/pgtable-prot.h         |   8 +-
 arch/arm64/include/asm/pgtable.h              |  26 +++-
 arch/arm64/include/asm/pkeys.h                | 110 ++++++++++++++
 arch/arm64/include/asm/por.h                  |  33 +++++
 arch/arm64/include/asm/processor.h            |   1 +
 arch/arm64/include/asm/sysreg.h               |  16 ++
 arch/arm64/include/asm/traps.h                |   1 +
 arch/arm64/include/uapi/asm/hwcap.h           |   1 +
 arch/arm64/include/uapi/asm/sigcontext.h      |   7 +
 arch/arm64/kernel/cpufeature.c                |  23 +++
 arch/arm64/kernel/cpuinfo.c                   |   1 +
 arch/arm64/kernel/process.c                   |  19 +++
 arch/arm64/kernel/signal.c                    |  51 +++++++
 arch/arm64/kernel/traps.c                     |  12 +-
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h    |  10 ++
 arch/arm64/kvm/sys_regs.c                     |   2 +
 arch/arm64/mm/fault.c                         |  44 +++++-
 arch/arm64/mm/mmap.c                          |   9 ++
 arch/arm64/mm/mmu.c                           |  40 +++++
 arch/arm64/tools/cpucaps                      |   1 +
 arch/arm64/tools/sysreg                       |  15 +-
 arch/powerpc/include/asm/page.h               |  11 ++
 arch/x86/include/asm/page.h                   |  10 ++
 fs/proc/task_mmu.c                            |   2 +
 include/linux/mm.h                            |  13 --
 tools/testing/selftests/arm64/abi/hwcap.c     |  13 ++
 .../testing/selftests/arm64/signal/.gitignore |   1 +
 .../arm64/signal/testcases/poe_siginfo.c      |  86 +++++++++++
 .../arm64/signal/testcases/testcases.c        |  27 +---
 .../arm64/signal/testcases/testcases.h        |  28 +++-
 .../selftests/kvm/aarch64/get-reg-list.c      |  14 ++
 tools/testing/selftests/mm/Makefile           |   2 +-
 tools/testing/selftests/mm/pkey-arm64.h       | 138 ++++++++++++++++++
 tools/testing/selftests/mm/pkey-helpers.h     |   8 +
 tools/testing/selftests/mm/pkey-powerpc.h     |   3 +
 tools/testing/selftests/mm/pkey-x86.h         |   4 +
 tools/testing/selftests/mm/protection_keys.c  |  29 ++--
 49 files changed, 880 insertions(+), 66 deletions(-)
 create mode 100644 arch/arm64/include/asm/pkeys.h
 create mode 100644 arch/arm64/include/asm/por.h
 create mode 100644 tools/testing/selftests/arm64/signal/testcases/poe_siginfo.c
 create mode 100644 tools/testing/selftests/mm/pkey-arm64.h

-- 
2.25.1

[PATCH v2 01/24] arm64/sysreg: add system register POR_EL{0,1}

[Joey Gouly]

Add POR_EL{0,1} according to DDI0601 2023-03.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
---
 arch/arm64/include/asm/sysreg.h | 13 +++++++++++++
 arch/arm64/tools/sysreg         | 12 ++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 38296579a4fd..cc2d61fd45c3 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -994,6 +994,19 @@
 
 #define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))
 
+/*
+ * Permission Overlay Extension (POE) permission encodings.
+ */
+#define POE_NONE	UL(0x0)
+#define POE_R		UL(0x1)
+#define POE_X		UL(0x2)
+#define POE_RX		UL(0x3)
+#define POE_W		UL(0x4)
+#define POE_RW		UL(0x5)
+#define POE_XW		UL(0x6)
+#define POE_RXW		UL(0x7)
+#define POE_MASK	UL(0xf)
+
 #define ARM64_FEATURE_FIELD_BITS	4
 
 /* Defined for compatibility only, do not add new users. */
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 76ce150e7347..dd91d0639bab 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -2504,6 +2504,18 @@ Sysreg	PIR_EL2		3	4	10	2	3
 Fields	PIRx_ELx
 EndSysreg
 
+Sysreg	POR_EL0		3	3	10	2	4
+Fields	PIRx_ELx
+EndSysreg
+
+Sysreg	POR_EL1		3	0	10	2	4
+Fields	PIRx_ELx
+EndSysreg
+
+Sysreg	POR_EL12	3	5	10	2	4
+Fields	PIRx_ELx
+EndSysreg
+
 Sysreg	LORSA_EL1	3	0	10	4	0
 Res0	63:52
 Field	51:16	SA
-- 
2.25.1

[PATCH v2 02/24] arm64/sysreg: update CPACR_EL1 register

[Joey Gouly]

Add E0POE bit that traps accesses to POR_EL0 from EL0.
Updated according to DDI0601 2023-03.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
---
 arch/arm64/tools/sysreg | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index dd91d0639bab..6952987f8363 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1741,7 +1741,8 @@ Field	0	M
 EndSysreg
 
 SysregFields	CPACR_ELx
-Res0	63:29
+Res0	63:30
+Field	29	E0POE
 Field	28	TTA
 Res0	27:26
 Field	25:24	SMEN
-- 
2.25.1

[PATCH v2 03/24] arm64: cpufeature: add Permission Overlay Extension cpucap

[Joey Gouly]

This indicates if the system supports POE. This is a CPUCAP_BOOT_CPU_FEATURE
as the boot CPU will enable POE if it has it, so secondary CPUs must also
have this feature.

Add a new config option: ARM64_POE

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig             | 16 ++++++++++++++++
 arch/arm64/kernel/cpufeature.c |  9 +++++++++
 arch/arm64/tools/cpucaps       |  1 +
 3 files changed, 26 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b10515c0200b..1f1a12e28c3f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2060,6 +2060,22 @@ config ARM64_EPAN
 	  if the cpu does not implement the feature.
 endmenu # "ARMv8.7 architectural features"
 
+menu "ARMv8.9 architectural features"
+config ARM64_POE
+	prompt "Permission Overlay Extension"
+	def_bool y
+	help
+	  The Permission Overlay Extension is used to implement Memory
+	  Protection Keys. Memory Protection Keys provides a mechanism for
+	  enforcing page-based protections, but without requiring modification
+	  of the page tables when an application changes protection domains.
+
+	  For details, see Documentation/core-api/protection-keys.rst
+
+	  If unsure, say y.
+
+endmenu # "ARMv8.9 architectural features"
+
 config ARM64_SVE
 	bool "ARM Scalable Vector Extension support"
 	default y
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 444a73c2e638..f1c1f348a31d 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2719,6 +2719,15 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP)
 	},
+#ifdef CONFIG_ARM64_POE
+	{
+		.desc = "Stage-1 Permission Overlay Extension (S1POE)",
+		.capability = ARM64_HAS_S1POE,
+		.type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
+		.matches = has_cpuid_feature,
+		ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, S1POE, IMP)
+	},
+#endif
 	{},
 };
 
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index c3f06fdef609..b8348e40f6d9 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -43,6 +43,7 @@ HAS_NO_FPSIMD
 HAS_NO_HW_PREFETCH
 HAS_PAN
 HAS_S1PIE
+HAS_S1POE
 HAS_RAS_EXTN
 HAS_RNG
 HAS_SB
-- 
2.25.1

[PATCH v2 04/24] arm64: disable trapping of POR_EL0 to EL2

[Joey Gouly]

Allow EL0 or EL1 to access POR_EL0 without being trapped to EL2.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/el2_setup.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index b7afaa026842..df5614be4b70 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -184,12 +184,20 @@
 .Lset_pie_fgt_\@:
 	mrs_s	x1, SYS_ID_AA64MMFR3_EL1
 	ubfx	x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4
-	cbz	x1, .Lset_fgt_\@
+	cbz	x1, .Lset_poe_fgt_\@
 
 	/* Disable trapping of PIR_EL1 / PIRE0_EL1 */
 	orr	x0, x0, #HFGxTR_EL2_nPIR_EL1
 	orr	x0, x0, #HFGxTR_EL2_nPIRE0_EL1
 
+.Lset_poe_fgt_\@:
+	mrs_s	x1, SYS_ID_AA64MMFR3_EL1
+	ubfx	x1, x1, #ID_AA64MMFR3_EL1_S1POE_SHIFT, #4
+	cbz	x1, .Lset_fgt_\@
+
+	/* Disable trapping of POR_EL0 */
+	orr	x0, x0, #HFGxTR_EL2_nPOR_EL0
+
 .Lset_fgt_\@:
 	msr_s	SYS_HFGRTR_EL2, x0
 	msr_s	SYS_HFGWTR_EL2, x0
-- 
2.25.1

[PATCH v2 05/24] arm64: context switch POR_EL0 register

[Joey Gouly]

POR_EL0 is a register that can be modified by userspace directly,
so it must be context switched.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/cpufeature.h |  6 ++++++
 arch/arm64/include/asm/processor.h  |  1 +
 arch/arm64/include/asm/sysreg.h     |  3 +++
 arch/arm64/kernel/process.c         | 19 +++++++++++++++++++
 4 files changed, 29 insertions(+)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 5bba39376055..019af90a3cf4 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -831,6 +831,12 @@ static inline bool system_supports_tlb_range(void)
 		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
 }
 
+static inline bool system_supports_poe(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_POE) &&
+		alternative_has_cap_unlikely(ARM64_HAS_S1POE);
+}
+
 int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index e5bc54522e71..b3ad719c2d0c 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -179,6 +179,7 @@ struct thread_struct {
 	u64			sctlr_user;
 	u64			svcr;
 	u64			tpidr2_el0;
+	u64			por_el0;
 };
 
 static inline unsigned int thread_get_vl(struct thread_struct *thread,
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cc2d61fd45c3..32270823a40b 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1007,6 +1007,9 @@
 #define POE_RXW		UL(0x7)
 #define POE_MASK	UL(0xf)
 
+/* Initial value for Permission Overlay Extension for EL0 */
+#define POR_EL0_INIT	POE_RXW
+
 #define ARM64_FEATURE_FIELD_BITS	4
 
 /* Defined for compatibility only, do not add new users. */
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 0fcc4eb1a7ab..9caed797fc47 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -271,12 +271,19 @@ static void flush_tagged_addr_state(void)
 		clear_thread_flag(TIF_TAGGED_ADDR);
 }
 
+static void flush_poe(void)
+{
+	if (system_supports_poe())
+		write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
+}
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
 	flush_tagged_addr_state();
+	flush_poe();
 }
 
 void arch_release_task_struct(struct task_struct *tsk)
@@ -498,6 +505,17 @@ static void erratum_1418040_new_exec(void)
 	preempt_enable();
 }
 
+static void permission_overlay_switch(struct task_struct *next)
+{
+	if (system_supports_poe()) {
+		current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
+		if (current->thread.por_el0 != next->thread.por_el0) {
+			write_sysreg_s(next->thread.por_el0, SYS_POR_EL0);
+			isb();
+		}
+	}
+}
+
 /*
  * __switch_to() checks current->thread.sctlr_user as an optimisation. Therefore
  * this function must be called with preemption disabled and the update to
@@ -533,6 +551,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	ssbs_thread_switch(next);
 	erratum_1418040_thread_switch(next);
 	ptrauth_thread_switch_user(next);
+	permission_overlay_switch(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
-- 
2.25.1

[PATCH v2 06/24] KVM: arm64: Save/restore POE registers

[Joey Gouly]

Define the new system registers that POE introduces and context switch them.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h           |  4 ++--
 arch/arm64/include/asm/kvm_host.h          |  4 ++++
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 10 ++++++++++
 arch/arm64/kvm/sys_regs.c                  |  2 ++
 4 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 5882b2415596..4022e69e17fd 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -344,14 +344,14 @@
  */
 #define __HFGRTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51))
 #define __HFGRTR_EL2_MASK	GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK	(GENMASK(55, 54) | BIT(50))
+#define __HFGRTR_EL2_nMASK	(GENMASK(60, 59) | GENMASK(55, 54) | BIT(50))
 
 #define __HFGWTR_EL2_RES0	(GENMASK(63, 56) | GENMASK(53, 51) |	\
 				 BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
 				 GENMASK(26, 25) | BIT(21) | BIT(18) |	\
 				 GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
 #define __HFGWTR_EL2_MASK	GENMASK(49, 0)
-#define __HFGWTR_EL2_nMASK	(GENMASK(55, 54) | BIT(50))
+#define __HFGWTR_EL2_nMASK	(GENMASK(60, 59) | GENMASK(55, 54) | BIT(50))
 
 #define __HFGITR_EL2_RES0	GENMASK(63, 57)
 #define __HFGITR_EL2_MASK	GENMASK(54, 0)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index af06ccb7ee34..205653bc5c2c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -365,6 +365,10 @@ enum vcpu_sysreg {
 	PIR_EL1,       /* Permission Indirection Register 1 (EL1) */
 	PIRE0_EL1,     /*  Permission Indirection Register 0 (EL1) */
 
+	/* Permission Overlay Extension registers */
+	POR_EL1,	/* Permission Overlay Register 1 (EL1) */
+	POR_EL0,	/* Permission Overlay Register 0 (EL0) */
+
 	/* 32bit specific registers. */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index bb6b571ec627..22f07ee43e7e 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -19,6 +19,9 @@
 static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt_sys_reg(ctxt, MDSCR_EL1)	= read_sysreg(mdscr_el1);
+
+	if (system_supports_poe())
+		ctxt_sys_reg(ctxt, POR_EL0)	= read_sysreg_s(SYS_POR_EL0);
 }
 
 static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
@@ -59,6 +62,8 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 		ctxt_sys_reg(ctxt, PIR_EL1)	= read_sysreg_el1(SYS_PIR);
 		ctxt_sys_reg(ctxt, PIRE0_EL1)	= read_sysreg_el1(SYS_PIRE0);
 	}
+	if (system_supports_poe())
+		ctxt_sys_reg(ctxt, POR_EL1)	= read_sysreg_el1(SYS_POR);
 	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg_par();
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
@@ -89,6 +94,9 @@ static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt_sys_reg(ctxt, MDSCR_EL1),  mdscr_el1);
+
+	if (system_supports_poe())
+		write_sysreg_s(ctxt_sys_reg(ctxt, POR_EL0),	SYS_POR_EL0);
 }
 
 static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
@@ -135,6 +143,8 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 		write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1),	SYS_PIR);
 		write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1),	SYS_PIRE0);
 	}
+	if (system_supports_poe())
+		write_sysreg_el1(ctxt_sys_reg(ctxt, POR_EL1),	SYS_POR);
 	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
 	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e92ec810d449..7d66cc7e104c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2124,6 +2124,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
 	{ SYS_DESC(SYS_PIRE0_EL1), access_vm_reg, reset_unknown, PIRE0_EL1 },
 	{ SYS_DESC(SYS_PIR_EL1), access_vm_reg, reset_unknown, PIR_EL1 },
+	{ SYS_DESC(SYS_POR_EL1), NULL, reset_unknown, POR_EL1 },
 	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
 
 	{ SYS_DESC(SYS_LORSA_EL1), trap_loregion },
@@ -2203,6 +2204,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ PMU_SYS_REG(PMOVSSET_EL0),
 	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
 
+	{ SYS_DESC(SYS_POR_EL0), NULL, reset_unknown, POR_EL0 },
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
 	{ SYS_DESC(SYS_TPIDR2_EL0), undef_access },
-- 
2.25.1

[PATCH v2 07/24] arm64: enable the Permission Overlay Extension for EL0

[Joey Gouly]

Expose a HWCAP and ID_AA64MMFR3_EL1_S1POE to userspace, so they can be used to
check if the CPU supports the feature.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 Documentation/arch/arm64/elf_hwcaps.rst |  3 +++
 arch/arm64/include/asm/hwcap.h          |  1 +
 arch/arm64/include/uapi/asm/hwcap.h     |  1 +
 arch/arm64/kernel/cpufeature.c          | 14 ++++++++++++++
 arch/arm64/kernel/cpuinfo.c             |  1 +
 5 files changed, 20 insertions(+)

diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst
index 76ff9d7398fd..85f6e9babc7f 100644
--- a/Documentation/arch/arm64/elf_hwcaps.rst
+++ b/Documentation/arch/arm64/elf_hwcaps.rst
@@ -308,6 +308,9 @@ HWCAP2_MOPS
 HWCAP2_HBC
     Functionality implied by ID_AA64ISAR2_EL1.BC == 0b0001.
 
+HWCAP2_POE
+    Functionality implied by ID_AA64MMFR3_EL1.S1POE == 0b0001.
+
 4. Unused AT_HWCAP bits
 -----------------------
 
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 521267478d18..196f21b7d11b 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -139,6 +139,7 @@
 #define KERNEL_HWCAP_SME_F16F16		__khwcap2_feature(SME_F16F16)
 #define KERNEL_HWCAP_MOPS		__khwcap2_feature(MOPS)
 #define KERNEL_HWCAP_HBC		__khwcap2_feature(HBC)
+#define KERNEL_HWCAP_POE		__khwcap2_feature(POE)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 53026f45a509..8809ff35d6e4 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -104,5 +104,6 @@
 #define HWCAP2_SME_F16F16	(1UL << 42)
 #define HWCAP2_MOPS		(1UL << 43)
 #define HWCAP2_HBC		(1UL << 44)
+#define HWCAP2_POE		(1UL << 46)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f1c1f348a31d..c79f43dfb2be 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -400,6 +400,8 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr3[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_POE),
+		       FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_S1POE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_S1PIE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_TCRX_SHIFT, 4, 0),
 	ARM64_FTR_END,
@@ -2220,6 +2222,14 @@ static void cpu_enable_mops(const struct arm64_cpu_capabilities *__unused)
 	sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_MSCEn);
 }
 
+#ifdef CONFIG_ARM64_POE
+static void cpu_enable_poe(const struct arm64_cpu_capabilities *__unused)
+{
+	sysreg_clear_set(REG_TCR2_EL1, 0, TCR2_EL1x_E0POE);
+	sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_E0POE);
+}
+#endif
+
 /* Internal helper functions to match cpu capability type */
 static bool
 cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -2725,6 +2735,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.capability = ARM64_HAS_S1POE,
 		.type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
 		.matches = has_cpuid_feature,
+		.cpu_enable = cpu_enable_poe,
 		ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, S1POE, IMP)
 	},
 #endif
@@ -2874,6 +2885,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
 #endif /* CONFIG_ARM64_SME */
+#ifdef CONFIG_ARM64_POE
+	HWCAP_CAP(ID_AA64MMFR3_EL1, S1POE, IMP, CAP_HWCAP, KERNEL_HWCAP_POE),
+#endif
 	{},
 };
 
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 98fda8500535..5b44e8ab9ab8 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -127,6 +127,7 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_SME_F16F16]	= "smef16f16",
 	[KERNEL_HWCAP_MOPS]		= "mops",
 	[KERNEL_HWCAP_HBC]		= "hbc",
+	[KERNEL_HWCAP_POE]		= "poe",
 };
 
 #ifdef CONFIG_COMPAT
-- 
2.25.1

[PATCH v2 08/24] arm64: add POIndex defines

[Joey Gouly]

The 3-bit POIndex is stored in the PTE at bits 60..62.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable-hwdef.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index e4944d517c99..fe270fa39110 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -178,6 +178,16 @@
 #define PTE_PI_IDX_2	53	/* PXN */
 #define PTE_PI_IDX_3	54	/* UXN */
 
+/*
+ * POIndex[2:0] encoding (Permission Overlay Extension)
+ */
+#define PTE_PO_IDX_0	(_AT(pteval_t, 1) << 60)
+#define PTE_PO_IDX_1	(_AT(pteval_t, 1) << 61)
+#define PTE_PO_IDX_2	(_AT(pteval_t, 1) << 62)
+
+#define PTE_PO_IDX_MASK		GENMASK_ULL(62, 60)
+
+
 /*
  * Memory Attribute override for Stage-2 (MemAttr[3:0])
  */
-- 
2.25.1

[PATCH v2 09/24] arm64: define VM_PKEY_BIT* for arm64

[Joey Gouly]

Define the VM_PKEY_BIT* values for arm64, and convert them into the arm64
specific pgprot values.

Move the current values for x86 and PPC into arch/*.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/mman.h   |  8 +++++++-
 arch/arm64/include/asm/page.h   | 10 ++++++++++
 arch/arm64/mm/mmap.c            |  9 +++++++++
 arch/powerpc/include/asm/page.h | 11 +++++++++++
 arch/x86/include/asm/page.h     | 10 ++++++++++
 fs/proc/task_mmu.c              |  2 ++
 include/linux/mm.h              | 13 -------------
 7 files changed, 49 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 5966ee4a6154..ecb2d18dc4d7 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/arch/arm64/include/asm/mman.h
@@ -7,7 +7,7 @@
 #include <uapi/asm/mman.h>
 
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
-	unsigned long pkey __always_unused)
+	unsigned long pkey)
 {
 	unsigned long ret = 0;
 
@@ -17,6 +17,12 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 	if (system_supports_mte() && (prot & PROT_MTE))
 		ret |= VM_MTE;
 
+#if defined(CONFIG_ARCH_HAS_PKEYS)
+	ret |= pkey & 0x1 ? VM_PKEY_BIT0 : 0;
+	ret |= pkey & 0x2 ? VM_PKEY_BIT1 : 0;
+	ret |= pkey & 0x4 ? VM_PKEY_BIT2 : 0;
+#endif
+
 	return ret;
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 2312e6ee595f..aabfda2516d2 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -49,6 +49,16 @@ int pfn_is_map_memory(unsigned long pfn);
 
 #define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
 
+#if defined(CONFIG_ARCH_HAS_PKEYS)
+/* A protection key is a 3-bit value */
+# define VM_PKEY_SHIFT	VM_HIGH_ARCH_BIT_2
+# define VM_PKEY_BIT0	VM_HIGH_ARCH_2
+# define VM_PKEY_BIT1	VM_HIGH_ARCH_3
+# define VM_PKEY_BIT2	VM_HIGH_ARCH_4
+# define VM_PKEY_BIT3	0
+# define VM_PKEY_BIT4	0
+#endif
+
 #include <asm-generic/getorder.h>
 
 #endif
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 8f5b7ce857ed..df4ece982375 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -98,6 +98,15 @@ pgprot_t vm_get_page_prot(unsigned long vm_flags)
 	if (vm_flags & VM_MTE)
 		prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED);
 
+#ifdef CONFIG_ARCH_HAS_PKEYS
+	if (vm_flags & VM_PKEY_BIT0)
+		prot |= PTE_PO_IDX_0;
+	if (vm_flags & VM_PKEY_BIT1)
+		prot |= PTE_PO_IDX_1;
+	if (vm_flags & VM_PKEY_BIT2)
+		prot |= PTE_PO_IDX_2;
+#endif
+
 	return __pgprot(prot);
 }
 EXPORT_SYMBOL(vm_get_page_prot);
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index e5fcc79b5bfb..a5e75ec333ad 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -330,6 +330,17 @@ static inline unsigned long kaslr_offset(void)
 }
 
 #include <asm-generic/memory_model.h>
+
+#if defined(CONFIG_ARCH_HAS_PKEYS)
+# define VM_PKEY_SHIFT	VM_HIGH_ARCH_BIT_0
+/* A protection key is a 5-bit value */
+# define VM_PKEY_BIT0	VM_HIGH_ARCH_0
+# define VM_PKEY_BIT1	VM_HIGH_ARCH_1
+# define VM_PKEY_BIT2	VM_HIGH_ARCH_2
+# define VM_PKEY_BIT3	VM_HIGH_ARCH_3
+# define VM_PKEY_BIT4	VM_HIGH_ARCH_4
+#endif /* CONFIG_ARCH_HAS_PKEYS */
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_PAGE_H */
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index d18e5c332cb9..b770db1a21e7 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -87,5 +87,15 @@ static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits)
 
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 
+#if defined(CONFIG_ARCH_HAS_PKEYS)
+# define VM_PKEY_SHIFT	VM_HIGH_ARCH_BIT_0
+/* A protection key is a 4-bit value */
+# define VM_PKEY_BIT0	VM_HIGH_ARCH_0
+# define VM_PKEY_BIT1	VM_HIGH_ARCH_1
+# define VM_PKEY_BIT2	VM_HIGH_ARCH_2
+# define VM_PKEY_BIT3	VM_HIGH_ARCH_3
+# define VM_PKEY_BIT4	0
+#endif /* CONFIG_ARCH_HAS_PKEYS */
+
 #endif	/* __KERNEL__ */
 #endif /* _ASM_X86_PAGE_H */
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3dd5be96691b..fcd94a39bb30 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -689,7 +689,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_PKEY_BIT0)]	= "",
 		[ilog2(VM_PKEY_BIT1)]	= "",
 		[ilog2(VM_PKEY_BIT2)]	= "",
+#if VM_PKEY_BIT3
 		[ilog2(VM_PKEY_BIT3)]	= "",
+#endif
 #if VM_PKEY_BIT4
 		[ilog2(VM_PKEY_BIT4)]	= "",
 #endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bf5d0b1b16f4..84ee022bf43e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -328,19 +328,6 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_HIGH_ARCH_5	BIT(VM_HIGH_ARCH_BIT_5)
 #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
 
-#ifdef CONFIG_ARCH_HAS_PKEYS
-# define VM_PKEY_SHIFT	VM_HIGH_ARCH_BIT_0
-# define VM_PKEY_BIT0	VM_HIGH_ARCH_0	/* A protection key is a 4-bit value */
-# define VM_PKEY_BIT1	VM_HIGH_ARCH_1	/* on x86 and 5-bit value on ppc64   */
-# define VM_PKEY_BIT2	VM_HIGH_ARCH_2
-# define VM_PKEY_BIT3	VM_HIGH_ARCH_3
-#ifdef CONFIG_PPC
-# define VM_PKEY_BIT4  VM_HIGH_ARCH_4
-#else
-# define VM_PKEY_BIT4  0
-#endif
-#endif /* CONFIG_ARCH_HAS_PKEYS */
-
 #ifdef CONFIG_X86_USER_SHADOW_STACK
 /*
  * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of
-- 
2.25.1

[PATCH v2 10/24] arm64: mask out POIndex when modifying a PTE

[Joey Gouly]

When a PTE is modified, the POIndex must be masked off so that it can be modified.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7f7d9b1df4e5..6c57ebe8e349 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -820,7 +820,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 */
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
 			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP |
-			      PTE_ATTRINDX_MASK;
+			      PTE_ATTRINDX_MASK | PTE_PO_IDX_MASK;
+
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
 		pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
-- 
2.25.1

[PATCH v2 11/24] arm64: enable ARCH_HAS_PKEYS on arm64

[Joey Gouly]

Enable the ARCH_HAS_PKEYS config, but provide dummy
functions for the entire interface.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig             |  2 ++
 arch/arm64/include/asm/pkeys.h | 54 ++++++++++++++++++++++++++++++++++
 arch/arm64/mm/mmu.c            |  7 +++++
 3 files changed, 63 insertions(+)
 create mode 100644 arch/arm64/include/asm/pkeys.h

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1f1a12e28c3f..68cfcbd95c8e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2064,6 +2064,8 @@ menu "ARMv8.9 architectural features"
 config ARM64_POE
 	prompt "Permission Overlay Extension"
 	def_bool y
+	select ARCH_USES_HIGH_VMA_FLAGS
+	select ARCH_HAS_PKEYS
 	help
 	  The Permission Overlay Extension is used to implement Memory
 	  Protection Keys. Memory Protection Keys provides a mechanism for
diff --git a/arch/arm64/include/asm/pkeys.h b/arch/arm64/include/asm/pkeys.h
new file mode 100644
index 000000000000..5761fb48fd53
--- /dev/null
+++ b/arch/arm64/include/asm/pkeys.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Arm Ltd.
+ *
+ * Based on arch/x86/include/asm/pkeys.h
+*/
+
+#ifndef _ASM_ARM64_PKEYS_H
+#define _ASM_ARM64_PKEYS_H
+
+#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2)
+
+#define arch_max_pkey() 0
+
+int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+		unsigned long init_val);
+
+static inline bool arch_pkeys_enabled(void)
+{
+	return false;
+}
+
+static inline int vma_pkey(struct vm_area_struct *vma)
+{
+	return -1;
+}
+
+static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
+		int prot, int pkey)
+{
+	return -1;
+}
+
+static inline int execute_only_pkey(struct mm_struct *mm)
+{
+	return -1;
+}
+
+static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
+{
+	return false;
+}
+
+static inline int mm_pkey_alloc(struct mm_struct *mm)
+{
+	return -1;
+}
+
+static inline int mm_pkey_free(struct mm_struct *mm, int pkey)
+{
+	return -EINVAL;
+}
+
+#endif /* _ASM_ARM64_PKEYS_H */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 47781bec6171..11765791b880 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1487,3 +1487,10 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte
 {
 	set_pte_at(vma->vm_mm, addr, ptep, pte);
 }
+
+#ifdef CONFIG_ARCH_HAS_PKEYS
+int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val)
+{
+	return -ENOSPC;
+}
+#endif
-- 
2.25.1

[PATCH v2 12/24] arm64: handle PKEY/POE faults

[Joey Gouly]

If a memory fault occurs that is due to an overlay/pkey fault, report that to
userspace with a SEGV_PKUERR.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/traps.h |  1 +
 arch/arm64/kernel/traps.c      | 12 ++++++++--
 arch/arm64/mm/fault.c          | 44 +++++++++++++++++++++++++++++++---
 3 files changed, 52 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index d66dfb3a72dd..dae51eccfc19 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -26,6 +26,7 @@ try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn)
 void force_signal_inject(int signal, int code, unsigned long address, unsigned long err);
 void arm64_notify_segfault(unsigned long addr);
 void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str);
+void arm64_force_sig_fault_pkey(int signo, int code, unsigned long far, const char *str, int pkey);
 void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str);
 void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str);
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 8b70759cdbb9..b68682c284a2 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -263,16 +263,24 @@ static void arm64_show_signal(int signo, const char *str)
 	__show_regs(regs);
 }
 
-void arm64_force_sig_fault(int signo, int code, unsigned long far,
-			   const char *str)
+void arm64_force_sig_fault_pkey(int signo, int code, unsigned long far,
+			   const char *str, int pkey)
 {
 	arm64_show_signal(signo, str);
 	if (signo == SIGKILL)
 		force_sig(SIGKILL);
+	else if (code == SEGV_PKUERR)
+		force_sig_pkuerr((void __user *)far, pkey);
 	else
 		force_sig_fault(signo, code, (void __user *)far);
 }
 
+void arm64_force_sig_fault(int signo, int code, unsigned long far,
+			   const char *str)
+{
+	arm64_force_sig_fault_pkey(signo, code, far, str, 0);
+}
+
 void arm64_force_sig_mceerr(int code, unsigned long far, short lsb,
 			    const char *str)
 {
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2e5d1e238af9..655dd80f0ec0 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -23,6 +23,7 @@
 #include <linux/sched/debug.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/pkeys.h>
 #include <linux/preempt.h>
 #include <linux/hugetlb.h>
 
@@ -497,6 +498,23 @@ static void do_bad_area(unsigned long far, unsigned long esr,
 #define VM_FAULT_BADMAP		((__force vm_fault_t)0x010000)
 #define VM_FAULT_BADACCESS	((__force vm_fault_t)0x020000)
 
+static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma,
+			unsigned int mm_flags)
+{
+	unsigned long iss2 = ESR_ELx_ISS2(esr);
+
+	if (!arch_pkeys_enabled())
+		return false;
+
+	if (iss2 & ESR_ELx_Overlay)
+		return true;
+
+	return !arch_vma_access_permitted(vma,
+			mm_flags & FAULT_FLAG_WRITE,
+			mm_flags & FAULT_FLAG_INSTRUCTION,
+			mm_flags & FAULT_FLAG_REMOTE);
+}
+
 static vm_fault_t __do_page_fault(struct mm_struct *mm,
 				  struct vm_area_struct *vma, unsigned long addr,
 				  unsigned int mm_flags, unsigned long vm_flags,
@@ -688,9 +706,29 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		 * Something tried to access memory that isn't in our memory
 		 * map.
 		 */
-		arm64_force_sig_fault(SIGSEGV,
-				      fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR,
-				      far, inf->name);
+		int fault_kind;
+		/*
+		 * The pkey value that we return to userspace can be different
+		 * from the pkey that caused the fault.
+		 *
+		 * 1. T1   : mprotect_key(foo, PAGE_SIZE, pkey=4);
+		 * 2. T1   : set AMR to deny access to pkey=4, touches, page
+		 * 3. T1   : faults...
+		 * 4.    T2: mprotect_key(foo, PAGE_SIZE, pkey=5);
+		 * 5. T1   : enters fault handler, takes mmap_lock, etc...
+		 * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
+		 *	     faulted on a pte with its pkey=4.
+		 */
+		int pkey = vma_pkey(vma);
+
+		if (fault_from_pkey(esr, vma, mm_flags))
+			fault_kind = SEGV_PKUERR;
+		else
+			fault_kind = fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR;
+
+		arm64_force_sig_fault_pkey(SIGSEGV,
+				      fault_kind,
+				      far, inf->name, pkey);
 	}
 
 	return 0;
-- 
2.25.1

[PATCH v2 13/24] arm64: stop using generic mm_hooks.h

[Joey Gouly]

These functions will be extended to support pkeys.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/mmu_context.h | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a6fb325424e7..c0eeed54225e 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -20,7 +20,6 @@
 #include <asm/cpufeature.h>
 #include <asm/daifflags.h>
 #include <asm/proc-fns.h>
-#include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
 #include <asm/sysreg.h>
 #include <asm/tlbflush.h>
@@ -209,6 +208,20 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	return 0;
 }
 
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+	return 0;
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+}
+
+static inline void arch_unmap(struct mm_struct *mm,
+			unsigned long start, unsigned long end)
+{
+}
+
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 static inline void update_saved_ttbr0(struct task_struct *tsk,
 				      struct mm_struct *mm)
@@ -298,6 +311,12 @@ static inline unsigned long mm_untag_mask(struct mm_struct *mm)
 	return -1UL >> 8;
 }
 
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool execute, bool foreign)
+{
+	return true;
+}
+
 #include <asm-generic/mmu_context.h>
 
 #endif /* !__ASSEMBLY__ */
-- 
2.25.1

[PATCH v2 14/24] arm64: implement PKEYS support

[Joey Gouly]

Implement the PKEYS interface, using the Permission Overlay Extension.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/mmu.h         |  2 +
 arch/arm64/include/asm/mmu_context.h | 32 ++++++++++++-
 arch/arm64/include/asm/pgtable.h     | 23 +++++++++-
 arch/arm64/include/asm/pkeys.h       | 68 +++++++++++++++++++++++++---
 arch/arm64/include/asm/por.h         | 33 ++++++++++++++
 arch/arm64/mm/mmu.c                  | 35 +++++++++++++-
 6 files changed, 184 insertions(+), 9 deletions(-)
 create mode 100644 arch/arm64/include/asm/por.h

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 94b68850cb9f..ed2cd66347d8 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -25,6 +25,8 @@ typedef struct {
 	refcount_t	pinned;
 	void		*vdso;
 	unsigned long	flags;
+
+	u8		pkey_allocation_map;
 } mm_context_t;
 
 /*
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index c0eeed54225e..aa739b87d49b 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -15,6 +15,7 @@
 #include <linux/sched/hotplug.h>
 #include <linux/mm_types.h>
 #include <linux/pgtable.h>
+#include <linux/pkeys.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
@@ -205,11 +206,24 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
 	atomic64_set(&mm->context.id, 0);
 	refcount_set(&mm->context.pinned, 0);
+
+	// pkey 0 is the default, so always reserve it.
+	mm->context.pkey_allocation_map = 0x1;
+
 	return 0;
 }
 
+static inline void arch_dup_pkeys(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
+{
+	/* Duplicate the oldmm pkey state in mm: */
+	mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map;
+}
+
 static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
+	arch_dup_pkeys(oldmm, mm);
+
 	return 0;
 }
 
@@ -311,10 +325,26 @@ static inline unsigned long mm_untag_mask(struct mm_struct *mm)
 	return -1UL >> 8;
 }
 
+/*
+ * We only want to enforce protection keys on the current process
+ * because we effectively have no access to POR_EL0 for other
+ * processes or any way to tell *which * POR_EL0 in a threaded
+ * process we could use.
+ *
+ * So do not enforce things if the VMA is not from the current
+ * mm, or if we are in a kernel thread.
+ */
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 		bool write, bool execute, bool foreign)
 {
-	return true;
+	if (!arch_pkeys_enabled())
+		return true;
+
+	/* allow access if the VMA is not one from this process */
+	if (foreign || vma_is_foreign(vma))
+		return true;
+
+	return por_el0_allows_pkey(vma_pkey(vma), write, execute);
 }
 
 #include <asm-generic/mmu_context.h>
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 6c57ebe8e349..8a1ff6ed917d 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -30,6 +30,7 @@
 
 #include <asm/cmpxchg.h>
 #include <asm/fixmap.h>
+#include <asm/por.h>
 #include <linux/mmdebug.h>
 #include <linux/mm_types.h>
 #include <linux/sched.h>
@@ -143,6 +144,24 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pte_accessible(mm, pte)	\
 	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
 
+static inline bool por_el0_allows_pkey(u8 pkey, bool write, bool execute)
+{
+	u64 por;
+
+	if (!system_supports_poe())
+		return true;
+
+	por = read_sysreg_s(SYS_POR_EL0);
+
+	if (write)
+		return por_elx_allows_write(por, pkey);
+
+	if (execute)
+		return por_elx_allows_exec(por, pkey);
+
+	return por_elx_allows_read(por, pkey);
+}
+
 /*
  * p??_access_permitted() is true for valid user mappings (PTE_USER
  * bit set, subject to the write permission check). For execute-only
@@ -151,7 +170,9 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
  * PTE_VALID bit set.
  */
 #define pte_access_permitted(pte, write) \
-	(((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte)))
+	(((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && \
+	 (!(write) || pte_write(pte)) && \
+	 por_el0_allows_pkey(FIELD_GET(PTE_PO_IDX_MASK, pte_val(pte)), write, false))
 #define pmd_access_permitted(pmd, write) \
 	(pte_access_permitted(pmd_pte(pmd), (write)))
 #define pud_access_permitted(pud, write) \
diff --git a/arch/arm64/include/asm/pkeys.h b/arch/arm64/include/asm/pkeys.h
index 5761fb48fd53..a80c654da93d 100644
--- a/arch/arm64/include/asm/pkeys.h
+++ b/arch/arm64/include/asm/pkeys.h
@@ -10,7 +10,7 @@
 
 #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2)
 
-#define arch_max_pkey() 0
+#define arch_max_pkey() 7
 
 int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 		unsigned long init_val);
@@ -22,33 +22,89 @@ static inline bool arch_pkeys_enabled(void)
 
 static inline int vma_pkey(struct vm_area_struct *vma)
 {
-	return -1;
+	return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT;
 }
 
 static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
 		int prot, int pkey)
 {
-	return -1;
+	if (pkey != -1)
+		return pkey;
+
+	return vma_pkey(vma);
 }
 
 static inline int execute_only_pkey(struct mm_struct *mm)
 {
+	// Execute-only mappings are handled by EPAN/FEAT_PAN3.
+	WARN_ON_ONCE(!cpus_have_final_cap(ARM64_HAS_EPAN));
+
 	return -1;
 }
 
+#define mm_pkey_allocation_map(mm)	(mm->context.pkey_allocation_map)
+#define mm_set_pkey_allocated(mm, pkey) do {		\
+	mm_pkey_allocation_map(mm) |= (1U << pkey);	\
+} while (0)
+#define mm_set_pkey_free(mm, pkey) do {			\
+	mm_pkey_allocation_map(mm) &= ~(1U << pkey);	\
+} while (0)
+
 static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
 {
-	return false;
+	/*
+	 * "Allocated" pkeys are those that have been returned
+	 * from pkey_alloc() or pkey 0 which is allocated
+	 * implicitly when the mm is created.
+	 */
+	if (pkey < 0)
+		return false;
+	if (pkey >= arch_max_pkey())
+		return false;
+
+	return mm_pkey_allocation_map(mm) & (1U << pkey);
 }
 
+/*
+ * Returns a positive, 3-bit key on success, or -1 on failure.
+ */
 static inline int mm_pkey_alloc(struct mm_struct *mm)
 {
-	return -1;
+	/*
+	 * Note: this is the one and only place we make sure
+	 * that the pkey is valid as far as the hardware is
+	 * concerned.  The rest of the kernel trusts that
+	 * only good, valid pkeys come out of here.
+	 */
+	u8 all_pkeys_mask = ((1U << arch_max_pkey()) - 1);
+	int ret;
+
+	if (!arch_pkeys_enabled())
+		return -1;
+
+	/*
+	 * Are we out of pkeys?  We must handle this specially
+	 * because ffz() behavior is undefined if there are no
+	 * zeros.
+	 */
+	if (mm_pkey_allocation_map(mm) == all_pkeys_mask)
+		return -1;
+
+	ret = ffz(mm_pkey_allocation_map(mm));
+
+	mm_set_pkey_allocated(mm, ret);
+
+	return ret;
 }
 
 static inline int mm_pkey_free(struct mm_struct *mm, int pkey)
 {
-	return -EINVAL;
+	if (!mm_pkey_is_allocated(mm, pkey))
+		return -EINVAL;
+
+	mm_set_pkey_free(mm, pkey);
+
+	return 0;
 }
 
 #endif /* _ASM_ARM64_PKEYS_H */
diff --git a/arch/arm64/include/asm/por.h b/arch/arm64/include/asm/por.h
new file mode 100644
index 000000000000..90484dae9920
--- /dev/null
+++ b/arch/arm64/include/asm/por.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Arm Ltd.
+*/
+
+#ifndef _ASM_ARM64_POR_H
+#define _ASM_ARM64_POR_H
+
+#define POR_BITS_PER_PKEY		4
+#define POR_ELx_IDX(por_elx, idx)	(((por_elx) >> (idx * POR_BITS_PER_PKEY)) & 0xf)
+
+static inline bool por_elx_allows_read(u64 por, u8 pkey)
+{
+	u8 perm = POR_ELx_IDX(por, pkey);
+
+	return perm & POE_R;
+}
+
+static inline bool por_elx_allows_write(u64 por, u8 pkey)
+{
+	u8 perm = POR_ELx_IDX(por, pkey);
+
+	return perm & POE_W;
+}
+
+static inline bool por_elx_allows_exec(u64 por, u8 pkey)
+{
+	u8 perm = POR_ELx_IDX(por, pkey);
+
+	return perm & POE_X;
+}
+
+#endif /* _ASM_ARM64_POR_H */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 11765791b880..eccf5a95ff30 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -25,6 +25,7 @@
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/kfence.h>
+#include <linux/pkeys.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>
@@ -1491,6 +1492,38 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte
 #ifdef CONFIG_ARCH_HAS_PKEYS
 int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val)
 {
-	return -ENOSPC;
+	u64 new_por = POE_RXW;
+	u64 old_por;
+	u64 pkey_shift;
+
+	if (!arch_pkeys_enabled())
+		return -ENOSPC;
+
+	/*
+	 * This code should only be called with valid 'pkey'
+	 * values originating from in-kernel users.  Complain
+	 * if a bad value is observed.
+	 */
+	if (WARN_ON_ONCE(pkey >= arch_max_pkey()))
+		return -EINVAL;
+
+	/* Set the bits we need in POR:  */
+	if (init_val & PKEY_DISABLE_ACCESS)
+		new_por = POE_X;
+	else if (init_val & PKEY_DISABLE_WRITE)
+		new_por = POE_RX;
+
+	/* Shift the bits in to the correct place in POR for pkey: */
+	pkey_shift = pkey * POR_BITS_PER_PKEY;
+	new_por <<= pkey_shift;
+
+	/* Get old POR and mask off any old bits in place: */
+	old_por = read_sysreg_s(SYS_POR_EL0);
+	old_por &= ~(POE_MASK << pkey_shift);
+
+	/* Write old part along with new part: */
+	write_sysreg_s(old_por | new_por, SYS_POR_EL0);
+
+	return 0;
 }
 #endif
-- 
2.25.1

[PATCH v2 15/24] arm64: add POE signal support

[Joey Gouly]

Add PKEY support to signals, by saving and restoring POR_EL0 from the stackframe.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/uapi/asm/sigcontext.h |  7 ++++
 arch/arm64/kernel/signal.c               | 51 ++++++++++++++++++++++++
 2 files changed, 58 insertions(+)

diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index f23c1dc3f002..cef85eeaf541 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -98,6 +98,13 @@ struct esr_context {
 	__u64 esr;
 };
 
+#define POE_MAGIC	0x504f4530
+
+struct poe_context {
+	struct _aarch64_ctx head;
+	__u64 por_el0;
+};
+
 /*
  * extra_context: describes extra space in the signal frame for
  * additional structures that don't fit in sigcontext.__reserved[].
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 0e8beb3349ea..379f364005bf 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -62,6 +62,7 @@ struct rt_sigframe_user_layout {
 	unsigned long zt_offset;
 	unsigned long extra_offset;
 	unsigned long end_offset;
+	unsigned long poe_offset;
 };
 
 #define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16)
@@ -182,6 +183,8 @@ struct user_ctxs {
 	u32 za_size;
 	struct zt_context __user *zt;
 	u32 zt_size;
+	struct poe_context __user *poe;
+	u32 poe_size;
 };
 
 static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
@@ -227,6 +230,20 @@ static int restore_fpsimd_context(struct user_ctxs *user)
 	return err ? -EFAULT : 0;
 }
 
+static int restore_poe_context(struct user_ctxs *user)
+{
+	u64 por_el0;
+	int err = 0;
+
+	if (user->poe_size != sizeof(*user->poe))
+		return -EINVAL;
+
+	__get_user_error(por_el0, &(user->poe->por_el0), err);
+	if (!err)
+		write_sysreg_s(por_el0, SYS_POR_EL0);
+
+	return err;
+}
 
 #ifdef CONFIG_ARM64_SVE
 
@@ -590,6 +607,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	user->tpidr2 = NULL;
 	user->za = NULL;
 	user->zt = NULL;
+	user->poe = NULL;
 
 	if (!IS_ALIGNED((unsigned long)base, 16))
 		goto invalid;
@@ -640,6 +658,17 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			/* ignore */
 			break;
 
+		case POE_MAGIC:
+			if (!system_supports_poe())
+				goto invalid;
+
+			if (user->poe)
+				goto invalid;
+
+			user->poe = (struct poe_context __user *)head;
+			user->poe_size = size;
+			break;
+
 		case SVE_MAGIC:
 			if (!system_supports_sve() && !system_supports_sme())
 				goto invalid;
@@ -812,6 +841,9 @@ static int restore_sigframe(struct pt_regs *regs,
 	if (err == 0 && system_supports_sme2() && user.zt)
 		err = restore_zt_context(&user);
 
+	if (err == 0 && system_supports_poe() && user.poe)
+		err = restore_poe_context(&user);
+
 	return err;
 }
 
@@ -928,6 +960,13 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 		}
 	}
 
+	if (system_supports_poe()) {
+		err = sigframe_alloc(user, &user->poe_offset,
+				     sizeof(struct poe_context));
+		if (err)
+			return err;
+	}
+
 	return sigframe_alloc_end(user);
 }
 
@@ -968,6 +1007,15 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
 	}
 
+	if (system_supports_poe() && err == 0 && user->poe_offset) {
+		struct poe_context __user *poe_ctx =
+			apply_user_offset(user, user->poe_offset);
+
+		__put_user_error(POE_MAGIC, &poe_ctx->head.magic, err);
+		__put_user_error(sizeof(*poe_ctx), &poe_ctx->head.size, err);
+		__put_user_error(read_sysreg_s(SYS_POR_EL0), &poe_ctx->por_el0, err);
+	}
+
 	/* Scalable Vector Extension state (including streaming), if present */
 	if ((system_supports_sve() || system_supports_sme()) &&
 	    err == 0 && user->sve_offset) {
@@ -1119,6 +1167,9 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		sme_smstop();
 	}
 
+	if (system_supports_poe())
+		write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
+
 	if (ka->sa.sa_flags & SA_RESTORER)
 		sigtramp = ka->sa.sa_restorer;
 	else
-- 
2.25.1

Re: [PATCH v2 15/24] arm64: add POE signal support

[Mark Brown]

[-- Attachment #1: Type: text/plain, Size: 190 bytes --]

On Fri, Oct 27, 2023 at 07:08:41PM +0100, Joey Gouly wrote:
> Add PKEY support to signals, by saving and restoring POR_EL0 from the stackframe.

Reviewed-by: Mark Brown <broonie@kernel.org>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

[PATCH v2 16/24] arm64: enable PKEY support for CPUs with S1POE

[Joey Gouly]

Now that PKEYs support has been implemented, enable it for CPUs that
support S1POE.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pkeys.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/pkeys.h b/arch/arm64/include/asm/pkeys.h
index a80c654da93d..23c473300058 100644
--- a/arch/arm64/include/asm/pkeys.h
+++ b/arch/arm64/include/asm/pkeys.h
@@ -17,7 +17,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 
 static inline bool arch_pkeys_enabled(void)
 {
-	return false;
+	return system_supports_poe();
 }
 
 static inline int vma_pkey(struct vm_area_struct *vma)
-- 
2.25.1

[PATCH v2 17/24] arm64: enable POE and PIE to coexist

[Joey Gouly]

Set the EL0/userspace indirection encodings to be the overlay enabled
variants of the permissions.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable-prot.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index eed814b00a38..06fb944ef252 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -141,10 +141,10 @@ extern bool arm64_use_ng_mappings;
 
 #define PIE_E0	( \
 	PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY),      PIE_X_O) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX)  | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RWX) | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY),      PIE_R)   | \
-	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED),        PIE_RW))
+	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O)  | \
+	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC),   PIE_RWX_O) | \
+	PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY),      PIE_R_O)   | \
+	PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED),        PIE_RW_O))
 
 #define PIE_E1	( \
 	PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY),      PIE_NONE_O) | \
-- 
2.25.1

[PATCH v2 18/24] kselftest/arm64: move get_header()

[Joey Gouly]

Put this function in the header so that it can be used by other tests, without
needing to link to testcases.c.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 .../arm64/signal/testcases/testcases.c        | 23 -----------------
 .../arm64/signal/testcases/testcases.h        | 25 +++++++++++++++++--
 2 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
index 9f580b55b388..fe950b6bca6b 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.c
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c
@@ -6,29 +6,6 @@
 
 #include "testcases.h"
 
-struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
-				size_t resv_sz, size_t *offset)
-{
-	size_t offs = 0;
-	struct _aarch64_ctx *found = NULL;
-
-	if (!head || resv_sz < HDR_SZ)
-		return found;
-
-	while (offs <= resv_sz - HDR_SZ &&
-	       head->magic != magic && head->magic) {
-		offs += head->size;
-		head = GET_RESV_NEXT_HEAD(head);
-	}
-	if (head->magic == magic) {
-		found = head;
-		if (offset)
-			*offset = offs;
-	}
-
-	return found;
-}
-
 bool validate_extra_context(struct extra_context *extra, char **err,
 			    void **extra_data, size_t *extra_size)
 {
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h
index a08ab0d6207a..d33154c9a4bd 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.h
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h
@@ -87,8 +87,29 @@ struct fake_sigframe {
 
 bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err);
 
-struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
-				size_t resv_sz, size_t *offset);
+static inline struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
+				size_t resv_sz, size_t *offset)
+{
+	size_t offs = 0;
+	struct _aarch64_ctx *found = NULL;
+
+	if (!head || resv_sz < HDR_SZ)
+		return found;
+
+	while (offs <= resv_sz - HDR_SZ &&
+	       head->magic != magic && head->magic) {
+		offs += head->size;
+		head = GET_RESV_NEXT_HEAD(head);
+	}
+	if (head->magic == magic) {
+		found = head;
+		if (offset)
+			*offset = offs;
+	}
+
+	return found;
+}
+
 
 static inline struct _aarch64_ctx *get_terminator(struct _aarch64_ctx *head,
 						  size_t resv_sz,
-- 
2.25.1

[PATCH v2 19/24] selftests: mm: move fpregs printing

[Joey Gouly]

arm64's fpregs are not at a constant offset from sigcontext. Since this is
not an important part of the test, don't print the fpregs pointer on arm64.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
---
 tools/testing/selftests/mm/pkey-powerpc.h    | 1 +
 tools/testing/selftests/mm/pkey-x86.h        | 2 ++
 tools/testing/selftests/mm/protection_keys.c | 6 ++++++
 3 files changed, 9 insertions(+)

diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index ae5df26104e5..6275d0f474b3 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -9,6 +9,7 @@
 #endif
 #define REG_IP_IDX		PT_NIP
 #define REG_TRAPNO		PT_TRAP
+#define MCONTEXT_FPREGS
 #define gregs			gp_regs
 #define fpregs			fp_regs
 #define si_pkey_offset		0x20
diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h
index 814758e109c0..b9170a26bfcb 100644
--- a/tools/testing/selftests/mm/pkey-x86.h
+++ b/tools/testing/selftests/mm/pkey-x86.h
@@ -15,6 +15,8 @@
 
 #endif
 
+#define MCONTEXT_FPREGS
+
 #ifndef PKEY_DISABLE_ACCESS
 # define PKEY_DISABLE_ACCESS	0x1
 #endif
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index 48dc151f8fca..b3dbd76ea27c 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -314,7 +314,9 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	ucontext_t *uctxt = vucontext;
 	int trapno;
 	unsigned long ip;
+#ifdef MCONTEXT_FPREGS
 	char *fpregs;
+#endif
 #if defined(__i386__) || defined(__x86_64__) /* arch */
 	u32 *pkey_reg_ptr;
 	int pkey_reg_offset;
@@ -330,7 +332,9 @@ 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];
+#ifdef MCONTEXT_FPREGS
 	fpregs = (char *) uctxt->uc_mcontext.fpregs;
+#endif
 
 	dprintf2("%s() trapno: %d ip: 0x%016lx info->si_code: %s/%d\n",
 			__func__, trapno, ip, si_code_str(si->si_code),
@@ -359,7 +363,9 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 #endif /* arch */
 
 	dprintf1("siginfo: %p\n", si);
+#ifdef MCONTEXT_FPREGS
 	dprintf1(" fpregs: %p\n", fpregs);
+#endif
 
 	if ((si->si_code == SEGV_MAPERR) ||
 	    (si->si_code == SEGV_ACCERR) ||
-- 
2.25.1

[PATCH v2 20/24] selftests: mm: make protection_keys test work on arm64

[Joey Gouly]

The encoding of the pkey register differs on arm64, than on x86/ppc. On those
platforms, a bit in the register is used to disable permissions, for arm64, a
bit enabled in the register indicates that the permission is allowed.

This drops two asserts of the form:
	 assert(read_pkey_reg() <= orig_pkey_reg);
Because on arm64 this doesn't hold, due to the encoding.

The pkey must be reset to both access allow and write allow in the signal
handler. pkey_access_allow() works currently for PowerPC as the
PKEY_DISABLE_ACCESS and PKEY_DISABLE_WRITE have overlapping bits set.

Access to the uc_mcontext is abstracted, as arm64 has a different structure.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
---
 .../arm64/signal/testcases/testcases.h        |   3 +
 tools/testing/selftests/mm/Makefile           |   2 +-
 tools/testing/selftests/mm/pkey-arm64.h       | 138 ++++++++++++++++++
 tools/testing/selftests/mm/pkey-helpers.h     |   8 +
 tools/testing/selftests/mm/pkey-powerpc.h     |   2 +
 tools/testing/selftests/mm/pkey-x86.h         |   2 +
 tools/testing/selftests/mm/protection_keys.c  |  23 +--
 7 files changed, 167 insertions(+), 11 deletions(-)
 create mode 100644 tools/testing/selftests/mm/pkey-arm64.h

diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h
index d33154c9a4bd..e445027d5ec2 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.h
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h
@@ -25,6 +25,9 @@
 #define HDR_SZ \
 	sizeof(struct _aarch64_ctx)
 
+#define GET_UC_RESV_HEAD(uc) \
+	(struct _aarch64_ctx *)(&(uc->uc_mcontext.__reserved))
+
 #define GET_SF_RESV_HEAD(sf) \
 	(struct _aarch64_ctx *)(&(sf).uc.uc_mcontext.__reserved)
 
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 6a9fc5693145..f50987233f55 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -95,7 +95,7 @@ TEST_GEN_FILES += $(BINARIES_64)
 endif
 else
 
-ifneq (,$(findstring $(ARCH),ppc64))
+ifneq (,$(filter $(ARCH),arm64 ppc64))
 TEST_GEN_FILES += protection_keys
 endif
 
diff --git a/tools/testing/selftests/mm/pkey-arm64.h b/tools/testing/selftests/mm/pkey-arm64.h
new file mode 100644
index 000000000000..3a5d8ba69bb7
--- /dev/null
+++ b/tools/testing/selftests/mm/pkey-arm64.h
@@ -0,0 +1,138 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Arm Ltd.
+*/
+
+#ifndef _PKEYS_ARM64_H
+#define _PKEYS_ARM64_H
+
+#include "vm_util.h"
+/* for signal frame parsing */
+#include "../arm64/signal/testcases/testcases.h"
+
+#ifndef SYS_mprotect_key
+# define SYS_mprotect_key	288
+#endif
+#ifndef SYS_pkey_alloc
+# define SYS_pkey_alloc		289
+# define SYS_pkey_free		290
+#endif
+#define MCONTEXT_IP(mc)		mc.pc
+#define MCONTEXT_TRAPNO(mc)	-1
+
+#define PKEY_MASK		0xf
+
+#define POE_X			0x2
+#define POE_RX			0x3
+#define POE_RWX			0x7
+
+#define NR_PKEYS		7
+#define NR_RESERVED_PKEYS	1 /* pkey-0 */
+
+#define PKEY_ALLOW_ALL		0x77777777
+
+#define PKEY_BITS_PER_PKEY	4
+#define PAGE_SIZE		sysconf(_SC_PAGESIZE)
+#undef HPAGE_SIZE
+#define HPAGE_SIZE		default_huge_page_size()
+
+/* 4-byte instructions * 16384 = 64K page */
+#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+
+static inline u64 __read_pkey_reg(void)
+{
+	u64 pkey_reg = 0;
+
+	// POR_EL0
+	asm volatile("mrs %0, S3_3_c10_c2_4" : "=r" (pkey_reg));
+
+	return pkey_reg;
+}
+
+static inline void __write_pkey_reg(u64 pkey_reg)
+{
+	u64 por = pkey_reg;
+
+	dprintf4("%s() changing %016llx to %016llx\n",
+			 __func__, __read_pkey_reg(), pkey_reg);
+
+	// POR_EL0
+	asm volatile("msr S3_3_c10_c2_4, %0\nisb" :: "r" (por) :);
+
+	dprintf4("%s() pkey register after changing %016llx to %016llx\n",
+			__func__, __read_pkey_reg(), pkey_reg);
+}
+
+static inline int cpu_has_pkeys(void)
+{
+	/* No simple way to determine this */
+	return 1;
+}
+
+static inline u32 pkey_bit_position(int pkey)
+{
+	return pkey * PKEY_BITS_PER_PKEY;
+}
+
+static inline int get_arch_reserved_keys(void)
+{
+	return NR_RESERVED_PKEYS;
+}
+
+void expect_fault_on_read_execonly_key(void *p1, int pkey)
+{
+}
+
+void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
+{
+	return PTR_ERR_ENOTSUP;
+}
+
+#define set_pkey_bits	set_pkey_bits
+static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags)
+{
+	u32 shift = pkey_bit_position(pkey);
+	u64 new_val = POE_RWX;
+
+	/* mask out bits from pkey in old value */
+	reg &= ~((u64)PKEY_MASK << shift);
+
+	if (flags & PKEY_DISABLE_ACCESS)
+		new_val = POE_X;
+	else if (flags & PKEY_DISABLE_WRITE)
+		new_val = POE_RX;
+
+	/* OR in new bits for pkey */
+	reg |= new_val << shift;
+
+	return reg;
+}
+
+#define get_pkey_bits	get_pkey_bits
+static inline u64 get_pkey_bits(u64 reg, int pkey)
+{
+	u32 shift = pkey_bit_position(pkey);
+	/*
+	 * shift down the relevant bits to the lowest two, then
+	 * mask off all the other higher bits
+	 */
+	u32 perm = (reg >> shift) & PKEY_MASK;
+
+	if (perm == POE_X)
+		return PKEY_DISABLE_ACCESS;
+	if (perm == POE_RX)
+		return PKEY_DISABLE_WRITE;
+	return 0;
+}
+
+static void aarch64_write_signal_pkey(ucontext_t *uctxt, u64 pkey)
+{
+	struct _aarch64_ctx *ctx = GET_UC_RESV_HEAD(uctxt);
+	struct poe_context *poe_ctx =
+		(struct poe_context *) get_header(ctx, POE_MAGIC,
+						sizeof(uctxt->uc_mcontext), NULL);
+	if (poe_ctx)
+		poe_ctx->por_el0 = pkey;
+}
+
+#endif /* _PKEYS_ARM64_H */
diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h
index 92f3be3dd8e5..07d131f98043 100644
--- a/tools/testing/selftests/mm/pkey-helpers.h
+++ b/tools/testing/selftests/mm/pkey-helpers.h
@@ -91,12 +91,17 @@ void record_pkey_malloc(void *ptr, long size, int prot);
 #include "pkey-x86.h"
 #elif defined(__powerpc64__) /* arch */
 #include "pkey-powerpc.h"
+#elif defined(__aarch64__) /* arch */
+#include "pkey-arm64.h"
 #else /* arch */
 #error Architecture not supported
 #endif /* arch */
 
+#ifndef PKEY_MASK
 #define PKEY_MASK	(PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)
+#endif
 
+#ifndef set_pkey_bits
 static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags)
 {
 	u32 shift = pkey_bit_position(pkey);
@@ -106,7 +111,9 @@ static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags)
 	reg |= (flags & PKEY_MASK) << shift;
 	return reg;
 }
+#endif
 
+#ifndef get_pkey_bits
 static inline u64 get_pkey_bits(u64 reg, int pkey)
 {
 	u32 shift = pkey_bit_position(pkey);
@@ -116,6 +123,7 @@ static inline u64 get_pkey_bits(u64 reg, int pkey)
 	 */
 	return ((reg >> shift) & PKEY_MASK);
 }
+#endif
 
 extern u64 shadow_pkey_reg;
 
diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index 6275d0f474b3..3d0c0bdae5bc 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -8,6 +8,8 @@
 # define SYS_pkey_free		385
 #endif
 #define REG_IP_IDX		PT_NIP
+#define MCONTEXT_IP(mc)		mc.gp_regs[REG_IP_IDX]
+#define MCONTEXT_TRAPNO(mc)	mc.gp_regs[REG_TRAPNO]
 #define REG_TRAPNO		PT_TRAP
 #define MCONTEXT_FPREGS
 #define gregs			gp_regs
diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h
index b9170a26bfcb..5f28e26a2511 100644
--- a/tools/testing/selftests/mm/pkey-x86.h
+++ b/tools/testing/selftests/mm/pkey-x86.h
@@ -15,6 +15,8 @@
 
 #endif
 
+#define MCONTEXT_IP(mc)		mc.gregs[REG_IP_IDX]
+#define MCONTEXT_TRAPNO(mc)	mc.gregs[REG_TRAPNO]
 #define MCONTEXT_FPREGS
 
 #ifndef PKEY_DISABLE_ACCESS
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index b3dbd76ea27c..14883d551531 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -147,7 +147,7 @@ void abort_hooks(void)
  * will then fault, which makes sure that the fault code handles
  * execute-only memory properly.
  */
-#ifdef __powerpc64__
+#if defined(__powerpc64__) || defined(__aarch64__)
 /* This way, both 4K and 64K alignment are maintained */
 __attribute__((__aligned__(65536)))
 #else
@@ -212,7 +212,6 @@ void pkey_disable_set(int pkey, int flags)
 	unsigned long syscall_flags = 0;
 	int ret;
 	int pkey_rights;
-	u64 orig_pkey_reg = read_pkey_reg();
 
 	dprintf1("START->%s(%d, 0x%x)\n", __func__,
 		pkey, flags);
@@ -242,8 +241,6 @@ void pkey_disable_set(int pkey, int flags)
 
 	dprintf1("%s(%d) pkey_reg: 0x%016llx\n",
 		__func__, pkey, read_pkey_reg());
-	if (flags)
-		pkey_assert(read_pkey_reg() >= orig_pkey_reg);
 	dprintf1("END<---%s(%d, 0x%x)\n", __func__,
 		pkey, flags);
 }
@@ -253,7 +250,6 @@ void pkey_disable_clear(int pkey, int flags)
 	unsigned long syscall_flags = 0;
 	int ret;
 	int pkey_rights = hw_pkey_get(pkey, syscall_flags);
-	u64 orig_pkey_reg = read_pkey_reg();
 
 	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
 
@@ -273,8 +269,6 @@ 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);
 }
 
 void pkey_write_allow(int pkey)
@@ -330,8 +324,8 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 			__func__, __LINE__,
 			__read_pkey_reg(), shadow_pkey_reg);
 
-	trapno = uctxt->uc_mcontext.gregs[REG_TRAPNO];
-	ip = uctxt->uc_mcontext.gregs[REG_IP_IDX];
+	trapno = MCONTEXT_TRAPNO(uctxt->uc_mcontext);
+	ip = MCONTEXT_IP(uctxt->uc_mcontext);
 #ifdef MCONTEXT_FPREGS
 	fpregs = (char *) uctxt->uc_mcontext.fpregs;
 #endif
@@ -395,6 +389,8 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 #elif defined(__powerpc64__) /* arch */
 	/* restore access and let the faulting instruction continue */
 	pkey_access_allow(siginfo_pkey);
+#elif defined(__aarch64__)
+	aarch64_write_signal_pkey(uctxt, PKEY_ALLOW_ALL);
 #endif /* arch */
 	pkey_faults++;
 	dprintf1("<<<<==================================================\n");
@@ -908,7 +904,9 @@ void expected_pkey_fault(int pkey)
 	 * test program continue.  We now have to restore it.
 	 */
 	if (__read_pkey_reg() != 0)
-#else /* arch */
+#elif defined(__aarch64__)
+	if (__read_pkey_reg() != PKEY_ALLOW_ALL)
+#else
 	if (__read_pkey_reg() != shadow_pkey_reg)
 #endif /* arch */
 		pkey_assert(0);
@@ -1498,6 +1496,11 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
 	lots_o_noops_around_write(&scratch);
 	do_not_expect_pkey_fault("executing on PROT_EXEC memory");
 	expect_fault_on_read_execonly_key(p1, pkey);
+
+	// Reset back to PROT_EXEC | PROT_READ for architectures that support
+	// non-PKEY execute-only permissions.
+	ret = mprotect_pkey(p1, PAGE_SIZE, PROT_EXEC | PROT_READ, (u64)pkey);
+	pkey_assert(!ret);
 }
 
 void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
-- 
2.25.1

[PATCH v2 21/24] kselftest/arm64: add HWCAP test for FEAT_S1POE

[Joey Gouly]

Check that when POE is enabled, the POR_EL0 register is accessible.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
---
 tools/testing/selftests/arm64/abi/hwcap.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index e3d262831d91..64bb49fe3f5c 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -101,6 +101,12 @@ static void pmull_sigill(void)
 	asm volatile(".inst 0x0ee0e000" : : : );
 }
 
+static void poe_sigill(void)
+{
+	/* mrs x0, POR_EL0 */
+	asm volatile("mrs x0, S3_3_C10_C2_4" : : : "x0");
+}
+
 static void rng_sigill(void)
 {
 	asm volatile("mrs x0, S3_3_C2_C4_0" : : : "x0");
@@ -379,6 +385,13 @@ static const struct hwcap_data {
 		.cpuinfo = "pmull",
 		.sigill_fn = pmull_sigill,
 	},
+	{
+		.name = "POE",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_POE,
+		.cpuinfo = "poe",
+		.sigill_fn = poe_sigill,
+	},
 	{
 		.name = "RNG",
 		.at_hwcap = AT_HWCAP2,
-- 
2.25.1

Re: [PATCH v2 21/24] kselftest/arm64: add HWCAP test for FEAT_S1POE

[Mark Brown]

[-- Attachment #1: Type: text/plain, Size: 326 bytes --]

On Fri, Oct 27, 2023 at 07:08:47PM +0100, Joey Gouly wrote:

> +	{
> +		.name = "POE",
> +		.at_hwcap = AT_HWCAP2,
> +		.hwcap_bit = HWCAP2_POE,
> +		.cpuinfo = "poe",
> +		.sigill_fn = poe_sigill,
> +	},

We should set sigill_reliable here - there's a trap for the POR_EL0 so
the test must fail if the hwcap isn't available.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

[PATCH v2 22/24] kselftest/arm64: parse POE_MAGIC in a signal frame

[Joey Gouly]

Teach the signal frame parsing about the new POE frame, avoids warning when it
is generated.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
---
 tools/testing/selftests/arm64/signal/testcases/testcases.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
index fe950b6bca6b..5dda753870aa 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.c
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c
@@ -161,6 +161,10 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			if (head->size != sizeof(struct esr_context))
 				*err = "Bad size for esr_context";
 			break;
+		case POE_MAGIC:
+			if (head->size != sizeof(struct poe_context))
+				*err = "Bad size for poe_context";
+			break;
 		case TPIDR2_MAGIC:
 			if (head->size != sizeof(struct tpidr2_context))
 				*err = "Bad size for tpidr2_context";
-- 
2.25.1

Re: [PATCH v2 22/24] kselftest/arm64: parse POE_MAGIC in a signal frame

[Mark Brown]

[-- Attachment #1: Type: text/plain, Size: 203 bytes --]

On Fri, Oct 27, 2023 at 07:08:48PM +0100, Joey Gouly wrote:
> Teach the signal frame parsing about the new POE frame, avoids warning when it
> is generated.

Reviewed-by: Mark Brown <broonie@kernel.org>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

[PATCH v2 23/24] kselftest/arm64: Add test case for POR_EL0 signal frame records

[Joey Gouly]

Ensure that we get signal context for POR_EL0 if and only if POE is present
on the system.

Copied from the TPIDR2 test.

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
---
 .../testing/selftests/arm64/signal/.gitignore |  1 +
 .../arm64/signal/testcases/poe_siginfo.c      | 86 +++++++++++++++++++
 2 files changed, 87 insertions(+)
 create mode 100644 tools/testing/selftests/arm64/signal/testcases/poe_siginfo.c

diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore
index 839e3a252629..6bcb27bd506b 100644
--- a/tools/testing/selftests/arm64/signal/.gitignore
+++ b/tools/testing/selftests/arm64/signal/.gitignore
@@ -5,6 +5,7 @@ sme_*
 ssve_*
 sve_*
 tpidr2_*
+poe_siginfo
 za_*
 zt_*
 !*.[ch]
diff --git a/tools/testing/selftests/arm64/signal/testcases/poe_siginfo.c b/tools/testing/selftests/arm64/signal/testcases/poe_siginfo.c
new file mode 100644
index 000000000000..d890029304c4
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/poe_siginfo.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Arm Limited
+ *
+ * Verify that the POR_EL0 register context in signal frames is set up as
+ * expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+#include <asm/sigcontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+#define SYS_POR_EL0 "S3_3_C10_C2_4"
+
+static uint64_t get_por_el0(void)
+{
+	uint64_t val;
+
+	asm volatile (
+		"mrs	%0, " SYS_POR_EL0 "\n"
+		: "=r"(val)
+		:
+		: "cc");
+
+	return val;
+}
+
+int poe_present(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct poe_context *poe_ctx;
+	size_t offset;
+	bool in_sigframe;
+	bool have_poe;
+	__u64 orig_poe;
+
+	have_poe = getauxval(AT_HWCAP2) & HWCAP2_POE;
+	if (have_poe)
+		orig_poe = get_por_el0();
+
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	poe_ctx = (struct poe_context *)
+		get_header(head, POE_MAGIC, td->live_sz, &offset);
+
+	in_sigframe = poe_ctx != NULL;
+
+	fprintf(stderr, "POR_EL0 sigframe %s on system %s POE\n",
+		in_sigframe ? "present" : "absent",
+		have_poe ? "with" : "without");
+
+	td->pass = (in_sigframe == have_poe);
+
+	/*
+	 * Check that the value we read back was the one present at
+	 * the time that the signal was triggered.
+	 */
+	if (have_poe && poe_ctx) {
+		if (poe_ctx->por_el0 != orig_poe) {
+			fprintf(stderr, "POR_EL0 in frame is %llx, was %llx\n",
+				poe_ctx->por_el0, orig_poe);
+			td->pass = false;
+		}
+	}
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "POR_EL0",
+	.descr = "Validate that POR_EL0 is present as expected",
+	.timeout = 3,
+	.run = poe_present,
+};
-- 
2.25.1

[PATCH v2 24/24] KVM: selftests: get-reg-list: add Permission Overlay registers

[Joey Gouly]

Add new system registers:
  - POR_EL1
  - POR_EL0

Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Shuah Khan <shuah@kernel.org>
---
 tools/testing/selftests/kvm/aarch64/get-reg-list.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 709d7d721760..ac661ebf6859 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -40,6 +40,18 @@ static struct feature_id_reg feat_id_regs[] = {
 		ARM64_SYS_REG(3, 0, 0, 7, 3),	/* ID_AA64MMFR3_EL1 */
 		4,
 		1
+	},
+	{
+		ARM64_SYS_REG(3, 0, 10, 2, 4),	/* POR_EL1 */
+		ARM64_SYS_REG(3, 0, 0, 7, 3),	/* ID_AA64MMFR3_EL1 */
+		16,
+		1
+	},
+	{
+		ARM64_SYS_REG(3, 3, 10, 2, 4),	/* POR_EL0 */
+		ARM64_SYS_REG(3, 0, 0, 7, 3),	/* ID_AA64MMFR3_EL1 */
+		16,
+		1
 	}
 };
 
@@ -468,6 +480,7 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(3, 0, 10, 2, 0),	/* MAIR_EL1 */
 	ARM64_SYS_REG(3, 0, 10, 2, 2),	/* PIRE0_EL1 */
 	ARM64_SYS_REG(3, 0, 10, 2, 3),	/* PIR_EL1 */
+	ARM64_SYS_REG(3, 0, 10, 2, 4),	/* POR_EL1 */
 	ARM64_SYS_REG(3, 0, 10, 3, 0),	/* AMAIR_EL1 */
 	ARM64_SYS_REG(3, 0, 12, 0, 0),	/* VBAR_EL1 */
 	ARM64_SYS_REG(3, 0, 12, 1, 1),	/* DISR_EL1 */
@@ -475,6 +488,7 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(3, 0, 13, 0, 4),	/* TPIDR_EL1 */
 	ARM64_SYS_REG(3, 0, 14, 1, 0),	/* CNTKCTL_EL1 */
 	ARM64_SYS_REG(3, 2, 0, 0, 0),	/* CSSELR_EL1 */
+	ARM64_SYS_REG(3, 3, 10, 2, 4),	/* POR_EL0 */
 	ARM64_SYS_REG(3, 3, 13, 0, 2),	/* TPIDR_EL0 */
 	ARM64_SYS_REG(3, 3, 13, 0, 3),	/* TPIDRRO_EL0 */
 	ARM64_SYS_REG(3, 3, 14, 0, 1),	/* CNTPCT_EL0 */
-- 
2.25.1