arm64 fixes for -rc4

- Work around Cavium/Marvell ThunderX2 erratum #219
 
 - Fix regression in mlock() ABI caused by sign-extension of TTBR1 addresses
 
 - More fixes to the spurious kernel fault detection logic
 
 - Fix pathological preemption race when enabling some CPU features at boot
 
 - Drop broken kcore macros in favour of generic implementations
 
 - Fix userspace view of ID_AA64ZFR0_EL1 when SVE is disabled
 
 - Avoid NULL dereference on allocation failure during hibernation
 -----BEGIN PGP SIGNATURE-----
 
 iQFEBAABCgAuFiEEPxTL6PPUbjXGY88ct6xw3ITBYzQFAl2o1IsQHHdpbGxAa2Vy
 bmVsLm9yZwAKCRC3rHDchMFjNEzXCACi8bK3PWUJ9R6DcUeDNFuSMT0d2C/8CRNj
 mKnYkHx/GSChLBe3ZsNYbH5wnh70ItKzUUyMwMlwKevpr0kvLn0AN+WuSpP77Thk
 qFuaO5EC10V039SXoAjOPs4Jxwoi6NaShDJYkLmr2kwp0g7dEol+8C80V1fQVqgx
 oSmFcrYlqki1qhz8e1qCY4K8fAt6VdMt8OcouXs58ETFqsUFBFy/xx9Vsa0AQKkN
 ZU8lzGIYNVLtA1G7wei7IuoKgYQ0t7XMynsve9P9i+RXmLrIbeyLpeZyn+3GW0jO
 r3Epj0lYqKe8IZ+eTUDu3KvKHHdICHIDBDxP2c66hfgkw0prn/vU
 =9E3e
 -----END PGP SIGNATURE-----

Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Will Deacon:
 "The main thing here is a long-awaited workaround for a CPU erratum on
  ThunderX2 which we have developed in conjunction with engineers from
  Cavium/Marvell.

  At the moment, the workaround is unconditionally enabled for affected
  CPUs at runtime but we may add a command-line option to disable it in
  future if performance numbers show up indicating a significant cost
  for real workloads.

  Summary:

   - Work around Cavium/Marvell ThunderX2 erratum #219

   - Fix regression in mlock() ABI caused by sign-extension of TTBR1 addresses

   - More fixes to the spurious kernel fault detection logic

   - Fix pathological preemption race when enabling some CPU features at boot

   - Drop broken kcore macros in favour of generic implementations

   - Fix userspace view of ID_AA64ZFR0_EL1 when SVE is disabled

   - Avoid NULL dereference on allocation failure during hibernation"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: tags: Preserve tags for addresses translated via TTBR1
  arm64: mm: fix inverted PAR_EL1.F check
  arm64: sysreg: fix incorrect definition of SYS_PAR_EL1_F
  arm64: entry.S: Do not preempt from IRQ before all cpufeatures are enabled
  arm64: hibernate: check pgd table allocation
  arm64: cpufeature: Treat ID_AA64ZFR0_EL1 as RAZ when SVE is not enabled
  arm64: Fix kcore macros after 52-bit virtual addressing fallout
  arm64: Allow CAVIUM_TX2_ERRATUM_219 to be selected
  arm64: Avoid Cavium TX2 erratum 219 when switching TTBR
  arm64: Enable workaround for Cavium TX2 erratum 219 when running SMT
  arm64: KVM: Trap VM ops when ARM64_WORKAROUND_CAVIUM_TX2_219_TVM is set

Documentation/arm64/silicon-errata.rst

@@ -107,6 +107,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Cavium         | ThunderX2 SMMUv3| #126            | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| Cavium         | ThunderX2 Core  | #219            | CAVIUM_TX2_ERRATUM_219      |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+

arch/arm64/Kconfig

@@ -616,6 +616,23 @@ config CAVIUM_ERRATUM_30115
 
 	  If unsure, say Y.
 
+config CAVIUM_TX2_ERRATUM_219
+	bool "Cavium ThunderX2 erratum 219: PRFM between TTBR change and ISB fails"
+	default y
+	help
+	  On Cavium ThunderX2, a load, store or prefetch instruction between a
+	  TTBR update and the corresponding context synchronizing operation can
+	  cause a spurious Data Abort to be delivered to any hardware thread in
+	  the CPU core.
+
+	  Work around the issue by avoiding the problematic code sequence and
+	  trapping KVM guest TTBRx_EL1 writes to EL2 when SMT is enabled. The
+	  trap handler performs the corresponding register access, skips the
+	  instruction and ensures context synchronization by virtue of the
+	  exception return.
+
+	  If unsure, say Y.
+
 config QCOM_FALKOR_ERRATUM_1003
 	bool "Falkor E1003: Incorrect translation due to ASID change"
 	default y

arch/arm64/include/asm/asm-uaccess.h

@@ -78,10 +78,9 @@ alternative_else_nop_endif
 /*
  * Remove the address tag from a virtual address, if present.
  */
-	.macro	clear_address_tag, dst, addr
-	tst	\addr, #(1 << 55)
-	bic	\dst, \addr, #(0xff << 56)
-	csel	\dst, \dst, \addr, eq
+	.macro	untagged_addr, dst, addr
+	sbfx	\dst, \addr, #0, #56
+	and	\dst, \dst, \addr
 	.endm
 
 #endif

arch/arm64/include/asm/cpucaps.h

@@ -52,7 +52,9 @@
 #define ARM64_HAS_IRQ_PRIO_MASKING		42
 #define ARM64_HAS_DCPODP			43
 #define ARM64_WORKAROUND_1463225		44
+#define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
+#define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
 
-#define ARM64_NCAPS				45
+#define ARM64_NCAPS				47
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/memory.h

@@ -215,12 +215,18 @@ static inline unsigned long kaslr_offset(void)
  * up with a tagged userland pointer. Clear the tag to get a sane pointer to
  * pass on to access_ok(), for instance.
  */
-#define untagged_addr(addr)	\
+#define __untagged_addr(addr)	\
 	((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
 
+#define untagged_addr(addr)	({					\
+	u64 __addr = (__force u64)addr;					\
+	__addr &= __untagged_addr(__addr);				\
+	(__force __typeof__(addr))__addr;				\
+})
+
 #ifdef CONFIG_KASAN_SW_TAGS
 #define __tag_shifted(tag)	((u64)(tag) << 56)
-#define __tag_reset(addr)	untagged_addr(addr)
+#define __tag_reset(addr)	__untagged_addr(addr)
 #define __tag_get(addr)		(__u8)((u64)(addr) >> 56)
 #else
 #define __tag_shifted(tag)	0UL

arch/arm64/include/asm/pgtable.h

@@ -876,9 +876,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 
 #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
 
-#define kc_vaddr_to_offset(v)	((v) & ~PAGE_END)
-#define kc_offset_to_vaddr(o)	((o) | PAGE_END)
-
 #ifdef CONFIG_ARM64_PA_BITS_52
 #define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
 #else

arch/arm64/include/asm/sysreg.h

@@ -212,7 +212,7 @@
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
-#define SYS_PAR_EL1_F			BIT(1)
+#define SYS_PAR_EL1_F			BIT(0)
 #define SYS_PAR_EL1_FST			GENMASK(6, 1)
 
 /*** Statistical Profiling Extension ***/

arch/arm64/kernel/cpu_errata.c

@@ -12,6 +12,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/smp_plat.h>
 
 static bool __maybe_unused
 is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
@@ -623,6 +624,30 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
 	return (need_wa > 0);
 }
 
+static const __maybe_unused struct midr_range tx2_family_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
+	{},
+};
+
+static bool __maybe_unused
+needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
+			 int scope)
+{
+	int i;
+
+	if (!is_affected_midr_range_list(entry, scope) ||
+	    !is_hyp_mode_available())
+		return false;
+
+	for_each_possible_cpu(i) {
+		if (MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0) != 0)
+			return true;
+	}
+
+	return false;
+}
+
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
 static const struct midr_range arm64_harden_el2_vectors[] = {
@@ -851,6 +876,19 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_cortex_a76_erratum_1463225,
 	},
+#endif
+#ifdef CONFIG_CAVIUM_TX2_ERRATUM_219
+	{
+		.desc = "Cavium ThunderX2 erratum 219 (KVM guest sysreg trapping)",
+		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_TVM,
+		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
+		.matches = needs_tx2_tvm_workaround,
+	},
+	{
+		.desc = "Cavium ThunderX2 erratum 219 (PRFM removal)",
+		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM,
+		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
+	},
 #endif
 	{
 	}

arch/arm64/kernel/cpufeature.c

@@ -176,11 +176,16 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 

arch/arm64/kernel/entry.S

@@ -604,7 +604,7 @@ el1_da:
 	 */
 	mrs	x3, far_el1
 	inherit_daif	pstate=x23, tmp=x2
-	clear_address_tag x0, x3
+	untagged_addr	x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort
 
@@ -680,7 +680,7 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	orr	x24, x24, x0
 alternative_else_nop_endif
 	cbnz	x24, 1f				// preempt count != 0 || NMI return path
-	bl	preempt_schedule_irq		// irq en/disable is done inside
+	bl	arm64_preempt_schedule_irq	// irq en/disable is done inside
 1:
 #endif
 
@@ -808,7 +808,7 @@ el0_da:
 	mrs	x26, far_el1
 	ct_user_exit_irqoff
 	enable_daif
-	clear_address_tag x0, x26
+	untagged_addr	x0, x26
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_mem_abort
@@ -1071,7 +1071,9 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
 #else
 	ldr	x30, =vectors
 #endif
+alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM
 	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
+alternative_else_nop_endif
 	msr	vbar_el1, x30
 	add	x30, x30, #(1b - tramp_vectors)
 	isb

arch/arm64/kernel/hibernate.c

@@ -201,6 +201,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 				 gfp_t mask)
 {
 	int rc = 0;
+	pgd_t *trans_pgd;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
@@ -215,7 +216,13 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	memcpy((void *)dst, src_start, length);
 	__flush_icache_range(dst, dst + length);
 
-	pgdp = pgd_offset_raw(allocator(mask), dst_addr);
+	trans_pgd = allocator(mask);
+	if (!trans_pgd) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
 		pudp = allocator(mask);
 		if (!pudp) {

arch/arm64/kernel/process.c

@@ -17,6 +17,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
+#include <linux/lockdep.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
@@ -44,6 +45,7 @@
 #include <asm/alternative.h>
 #include <asm/arch_gicv3.h>
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/cacheflush.h>
 #include <asm/exec.h>
 #include <asm/fpsimd.h>
@@ -631,3 +633,19 @@ static int __init tagged_addr_init(void)
 
 core_initcall(tagged_addr_init);
 #endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
+
+asmlinkage void __sched arm64_preempt_schedule_irq(void)
+{
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Preempting a task from an IRQ means we leave copies of PSTATE
+	 * on the stack. cpufeature's enable calls may modify PSTATE, but
+	 * resuming one of these preempted tasks would undo those changes.
+	 *
+	 * Only allow a task to be preempted once cpufeatures have been
+	 * enabled.
+	 */
+	if (static_branch_likely(&arm64_const_caps_ready))
+		preempt_schedule_irq();
+}

arch/arm64/kvm/hyp/switch.c

@@ -124,6 +124,9 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 hcr = vcpu->arch.hcr_el2;
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+		hcr |= HCR_TVM;
+
 	write_sysreg(hcr, hcr_el2);
 
 	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
@@ -174,8 +177,10 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 	 * the crucial bit is "On taking a vSError interrupt,
 	 * HCR_EL2.VSE is cleared to 0."
 	 */
-	if (vcpu->arch.hcr_el2 & HCR_VSE)
-		vcpu->arch.hcr_el2 = read_sysreg(hcr_el2);
+	if (vcpu->arch.hcr_el2 & HCR_VSE) {
+		vcpu->arch.hcr_el2 &= ~HCR_VSE;
+		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+	}
 
 	if (has_vhe())
 		deactivate_traps_vhe();
@@ -380,6 +385,61 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
+	int rt = kvm_vcpu_sys_get_rt(vcpu);
+	u64 val = vcpu_get_reg(vcpu, rt);
+
+	/*
+	 * The normal sysreg handling code expects to see the traps,
+	 * let's not do anything here.
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_TVM)
+		return false;
+
+	switch (sysreg) {
+	case SYS_SCTLR_EL1:
+		write_sysreg_el1(val, SYS_SCTLR);
+		break;
+	case SYS_TTBR0_EL1:
+		write_sysreg_el1(val, SYS_TTBR0);
+		break;
+	case SYS_TTBR1_EL1:
+		write_sysreg_el1(val, SYS_TTBR1);
+		break;
+	case SYS_TCR_EL1:
+		write_sysreg_el1(val, SYS_TCR);
+		break;
+	case SYS_ESR_EL1:
+		write_sysreg_el1(val, SYS_ESR);
+		break;
+	case SYS_FAR_EL1:
+		write_sysreg_el1(val, SYS_FAR);
+		break;
+	case SYS_AFSR0_EL1:
+		write_sysreg_el1(val, SYS_AFSR0);
+		break;
+	case SYS_AFSR1_EL1:
+		write_sysreg_el1(val, SYS_AFSR1);
+		break;
+	case SYS_MAIR_EL1:
+		write_sysreg_el1(val, SYS_MAIR);
+		break;
+	case SYS_AMAIR_EL1:
+		write_sysreg_el1(val, SYS_AMAIR);
+		break;
+	case SYS_CONTEXTIDR_EL1:
+		write_sysreg_el1(val, SYS_CONTEXTIDR);
+		break;
+	default:
+		return false;
+	}
+
+	__kvm_skip_instr(vcpu);
+	return true;
+}
+
 /*
  * Return true when we were able to fixup the guest exit and should return to
  * the guest, false when we should restore the host state and return to the
@@ -399,6 +459,11 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (*exit_code != ARM_EXCEPTION_TRAP)
 		goto exit;
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
+	    handle_tx2_tvm(vcpu))
+		return true;
+
 	/*
 	 * We trap the first access to the FP/SIMD to save the host context
 	 * and restore the guest context lazily.

arch/arm64/mm/fault.c

@@ -268,8 +268,12 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
 	par = read_sysreg(par_el1);
 	local_irq_restore(flags);
 
+	/*
+	 * If we now have a valid translation, treat the translation fault as
+	 * spurious.
+	 */
 	if (!(par & SYS_PAR_EL1_F))
-		return false;
+		return true;
 
 	/*
 	 * If we got a different type of fault from the AT instruction,

include/linux/sched.h

@@ -223,6 +223,7 @@ extern long schedule_timeout_uninterruptible(long timeout);
 extern long schedule_timeout_idle(long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
+asmlinkage void preempt_schedule_irq(void);
 
 extern int __must_check io_schedule_prepare(void);
 extern void io_schedule_finish(int token);