Merge branch 'for-next/poe' into for-next/core

* for-next/poe: (31 commits)
  arm64: pkeys: remove redundant WARN
  kselftest/arm64: Add test case for POR_EL0 signal frame records
  kselftest/arm64: parse POE_MAGIC in a signal frame
  kselftest/arm64: add HWCAP test for FEAT_S1POE
  selftests: mm: make protection_keys test work on arm64
  selftests: mm: move fpregs printing
  kselftest/arm64: move get_header()
  arm64: add Permission Overlay Extension Kconfig
  arm64: enable PKEY support for CPUs with S1POE
  arm64: enable POE and PIE to coexist
  arm64/ptrace: add support for FEAT_POE
  arm64: add POE signal support
  arm64: implement PKEYS support
  arm64: add pte_access_permitted_no_overlay()
  arm64: handle PKEY/POE faults
  arm64: mask out POIndex when modifying a PTE
  arm64: convert protection key into vm_flags and pgprot values
  arm64: add POIndex defines
  arm64: re-order MTE VM_ flags
  arm64: enable the Permission Overlay Extension for EL0
  ...

Documentation/arch/arm64/elf_hwcaps.rst

@@ -365,6 +365,8 @@ HWCAP2_SME_SF8DP2
 HWCAP2_SME_SF8DP4
     Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1.
 
+HWCAP2_POE
+    Functionality implied by ID_AA64MMFR3_EL1.S1POE == 0b0001.
 
 4. Unused AT_HWCAP bits
 -----------------------

arch/arm64/Kconfig

@@ -2138,6 +2138,29 @@ 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
+	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
+	  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.
+
+config ARCH_PKEY_BITS
+	int
+	default 3
+
+endmenu # "ARMv8.9 architectural features"
+
 config ARM64_SVE
 	bool "ARM Scalable Vector Extension support"
 	default y

arch/arm64/include/asm/cpufeature.h

@@ -832,6 +832,12 @@ static inline bool system_supports_lpa2(void)
 	return cpus_have_final_cap(ARM64_HAS_LPA2);
 }
 
+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);
 

arch/arm64/include/asm/el2_setup.h

@@ -192,6 +192,14 @@
 	orr	x0, x0, #HFGxTR_EL2_nPIRE0_EL1
 
 .Lskip_pie_fgt_\@:
+	mrs_s	x1, SYS_ID_AA64MMFR3_EL1
+	ubfx	x1, x1, #ID_AA64MMFR3_EL1_S1POE_SHIFT, #4
+	cbz	x1, .Lskip_poe_fgt_\@
+
+	/* Disable trapping of POR_EL0 */
+	orr	x0, x0, #HFGxTR_EL2_nPOR_EL0
+
+.Lskip_poe_fgt_\@:
 	msr_s	SYS_HFGRTR_EL2, x0
 	msr_s	SYS_HFGWTR_EL2, x0
 	msr_s	SYS_HFGITR_EL2, xzr

arch/arm64/include/asm/hwcap.h

@@ -157,6 +157,7 @@
 #define KERNEL_HWCAP_SME_SF8FMA		__khwcap2_feature(SME_SF8FMA)
 #define KERNEL_HWCAP_SME_SF8DP4		__khwcap2_feature(SME_SF8DP4)
 #define KERNEL_HWCAP_SME_SF8DP2		__khwcap2_feature(SME_SF8DP2)
+#define KERNEL_HWCAP_POE		__khwcap2_feature(POE)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/kvm_asm.h

@@ -10,6 +10,7 @@
 #include <asm/hyp_image.h>
 #include <asm/insn.h>
 #include <asm/virt.h>
+#include <asm/sysreg.h>
 
 #define ARM_EXIT_WITH_SERROR_BIT  31
 #define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
@@ -259,7 +260,7 @@ extern u64 __kvm_get_mdcr_el2(void);
 	asm volatile(							\
 	"	mrs	%1, spsr_el2\n"					\
 	"	mrs	%2, elr_el2\n"					\
-	"1:	at	"at_op", %3\n"					\
+	"1:	" __msr_s(at_op, "%3") "\n"				\
 	"	isb\n"							\
 	"	b	9f\n"						\
 	"2:	msr	spsr_el2, %1\n"					\

arch/arm64/include/asm/kvm_host.h

@@ -446,6 +446,8 @@ enum vcpu_sysreg {
 	GCR_EL1,	/* Tag Control Register */
 	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
 
+	POR_EL0,	/* Permission Overlay Register 0 (EL0) */
+
 	/* 32bit specific registers. */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -517,6 +519,8 @@ enum vcpu_sysreg {
 	VNCR(PIR_EL1),	 /* Permission Indirection Register 1 (EL1) */
 	VNCR(PIRE0_EL1), /*  Permission Indirection Register 0 (EL1) */
 
+	VNCR(POR_EL1),	/* Permission Overlay Register 1 (EL1) */
+
 	VNCR(HFGRTR_EL2),
 	VNCR(HFGWTR_EL2),
 	VNCR(HFGITR_EL2),

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 +17,14 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 	if (system_supports_mte() && (prot & PROT_MTE))
 		ret |= VM_MTE;
 
+#ifdef CONFIG_ARCH_HAS_PKEYS
+	if (system_supports_poe()) {
+		ret |= pkey & BIT(0) ? VM_PKEY_BIT0 : 0;
+		ret |= pkey & BIT(1) ? VM_PKEY_BIT1 : 0;
+		ret |= pkey & BIT(2) ? VM_PKEY_BIT2 : 0;
+	}
+#endif
+
 	return ret;
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)

arch/arm64/include/asm/mmu.h

@@ -25,6 +25,7 @@ typedef struct {
 	refcount_t	pinned;
 	void		*vdso;
 	unsigned long	flags;
+	u8		pkey_allocation_map;
 } mm_context_t;
 
 /*

arch/arm64/include/asm/mmu_context.h

@@ -15,12 +15,12 @@
 #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>
 #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>
@@ -175,9 +175,36 @@ 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 = BIT(0);
+
 	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;
+}
+
+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)
@@ -267,6 +294,23 @@ static inline unsigned long mm_untag_mask(struct mm_struct *mm)
 	return -1UL >> 8;
 }
 
+/*
+ * Only enforce protection keys on the current process, because there is no
+ * user context to access POR_EL0 for another address space.
+ */
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool execute, bool foreign)
+{
+	if (!system_supports_poe())
+		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>
 
 #endif /* !__ASSEMBLY__ */

arch/arm64/include/asm/pgtable-hwdef.h

@@ -198,6 +198,16 @@
 #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])
  */

arch/arm64/include/asm/pgtable-prot.h

@@ -154,10 +154,10 @@ static inline bool __pure lpa2_is_enabled(void)
 
 #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) | \

arch/arm64/include/asm/pgtable.h

@@ -34,6 +34,7 @@
 
 #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>
@@ -149,6 +150,24 @@ 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
@@ -156,8 +175,11 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
  * not set) must return false. PROT_NONE mappings do not have the
  * PTE_VALID bit set.
  */
-#define pte_access_permitted(pte, write) \
+#define pte_access_permitted_no_overlay(pte, write) \
 	(((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte)))
+#define pte_access_permitted(pte, write) \
+	(pte_access_permitted_no_overlay(pte, write) && \
+	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) \
@@ -373,10 +395,11 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages)
 	/*
 	 * If the PTE would provide user space access to the tags associated
 	 * with it then ensure that the MTE tags are synchronised.  Although
-	 * pte_access_permitted() returns false for exec only mappings, they
-	 * don't expose tags (instruction fetches don't check tags).
+	 * pte_access_permitted_no_overlay() returns false for exec only
+	 * mappings, they don't expose tags (instruction fetches don't check
+	 * tags).
 	 */
-	if (system_supports_mte() && pte_access_permitted(pte, false) &&
+	if (system_supports_mte() && pte_access_permitted_no_overlay(pte, false) &&
 	    !pte_special(pte) && pte_tagged(pte))
 		mte_sync_tags(pte, nr_pages);
 }
@@ -1103,7 +1126,8 @@ 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_PRESENT_INVALID | PTE_VALID | PTE_WRITE |
-			      PTE_GP | PTE_ATTRINDX_MASK;
+			      PTE_GP | 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));

arch/arm64/include/asm/pkeys.h

@@ -0,0 +1,106 @@
+/* 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() 8
+
+int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+		unsigned long init_val);
+
+static inline bool arch_pkeys_enabled(void)
+{
+	return system_supports_poe();
+}
+
+static inline int vma_pkey(struct vm_area_struct *vma)
+{
+	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)
+{
+	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.
+	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)
+{
+	/*
+	 * "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 || 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)
+{
+	/*
+	 * 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 = GENMASK(arch_max_pkey() - 1, 0);
+	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)
+{
+	if (!mm_pkey_is_allocated(mm, pkey))
+		return -EINVAL;
+
+	mm_set_pkey_free(mm, pkey);
+
+	return 0;
+}
+
+#endif /* _ASM_ARM64_PKEYS_H */

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 */

arch/arm64/include/asm/processor.h

@@ -184,6 +184,7 @@ 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,

arch/arm64/include/asm/sysreg.h

@@ -1076,6 +1076,9 @@
 #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. */

arch/arm64/include/asm/traps.h

@@ -25,6 +25,7 @@ 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(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);
 

arch/arm64/include/asm/vncr_mapping.h

@@ -52,6 +52,7 @@
 #define VNCR_PIRE0_EL1		0x290
 #define VNCR_PIRE0_EL2		0x298
 #define VNCR_PIR_EL1		0x2A0
+#define VNCR_POR_EL1		0x2A8
 #define VNCR_ICH_LR0_EL2        0x400
 #define VNCR_ICH_LR1_EL2        0x408
 #define VNCR_ICH_LR2_EL2        0x410

arch/arm64/include/uapi/asm/hwcap.h

@@ -122,5 +122,6 @@
 #define HWCAP2_SME_SF8FMA	(1UL << 60)
 #define HWCAP2_SME_SF8DP4	(1UL << 61)
 #define HWCAP2_SME_SF8DP2	(1UL << 62)
+#define HWCAP2_POE		(1UL << 63)
 
 #endif /* _UAPI__ASM_HWCAP_H */