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

Pull arm64 updates from Catalin Marinas:
 "Apart from the arm64-specific bits (core arch and perf, new arm64
  selftests), it touches the generic cow_user_page() (reviewed by
  Kirill) together with a macro for x86 to preserve the existing
  behaviour on this architecture.

  Summary:

   - On ARMv8 CPUs without hardware updates of the access flag, avoid
     failing cow_user_page() on PFN mappings if the pte is old. The
     patches introduce an arch_faults_on_old_pte() macro, defined as
     false on x86. When true, cow_user_page() makes the pte young before
     attempting __copy_from_user_inatomic().

   - Covert the synchronous exception handling paths in
     arch/arm64/kernel/entry.S to C.

   - FTRACE_WITH_REGS support for arm64.

   - ZONE_DMA re-introduced on arm64 to support Raspberry Pi 4

   - Several kselftest cases specific to arm64, together with a
     MAINTAINERS update for these files (moved to the ARM64 PORT entry).

   - Workaround for a Neoverse-N1 erratum where the CPU may fetch stale
     instructions under certain conditions.

   - Workaround for Cortex-A57 and A72 errata where the CPU may
     speculatively execute an AT instruction and associate a VMID with
     the wrong guest page tables (corrupting the TLB).

   - Perf updates for arm64: additional PMU topologies on HiSilicon
     platforms, support for CCN-512 interconnect, AXI ID filtering in
     the IMX8 DDR PMU, support for the CCPI2 uncore PMU in ThunderX2.

   - GICv3 optimisation to avoid a heavy barrier when accessing the
     ICC_PMR_EL1 register.

   - ELF HWCAP documentation updates and clean-up.

   - SMC calling convention conduit code clean-up.

   - KASLR diagnostics printed during boot

   - NVIDIA Carmel CPU added to the KPTI whitelist

   - Some arm64 mm clean-ups: use generic free_initrd_mem(), remove
     stale macro, simplify calculation in __create_pgd_mapping(), typos.

   - Kconfig clean-ups: CMDLINE_FORCE to depend on CMDLINE, choice for
     endinanness to help with allmodconfig"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (93 commits)
  arm64: Kconfig: add a choice for endianness
  kselftest: arm64: fix spelling mistake "contiguos" -> "contiguous"
  arm64: Kconfig: make CMDLINE_FORCE depend on CMDLINE
  MAINTAINERS: Add arm64 selftests to the ARM64 PORT entry
  arm64: kaslr: Check command line before looking for a seed
  arm64: kaslr: Announce KASLR status on boot
  kselftest: arm64: fake_sigreturn_misaligned_sp
  kselftest: arm64: fake_sigreturn_bad_size
  kselftest: arm64: fake_sigreturn_duplicated_fpsimd
  kselftest: arm64: fake_sigreturn_missing_fpsimd
  kselftest: arm64: fake_sigreturn_bad_size_for_magic0
  kselftest: arm64: fake_sigreturn_bad_magic
  kselftest: arm64: add helper get_current_context
  kselftest: arm64: extend test_init functionalities
  kselftest: arm64: mangle_pstate_invalid_mode_el[123][ht]
  kselftest: arm64: mangle_pstate_invalid_daif_bits
  kselftest: arm64: mangle_pstate_invalid_compat_toggle and common utils
  kselftest: arm64: extend toplevel skeleton Makefile
  drivers/perf: hisi: update the sccl_id/ccl_id for certain HiSilicon platform
  arm64: mm: reserve CMA and crashkernel in ZONE_DMA32
  ...

3 files changed, 100 insertions, 10 deletions

diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 799e84a40335..72fbbd86eb5e 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -12,7 +12,7 @@
 
 #include <kvm/arm_psci.h>
 
-#include <asm/arch_gicv3.h>
+#include <asm/barrier.h>
 #include <asm/cpufeature.h>
 #include <asm/kprobes.h>
 #include <asm/kvm_asm.h>
@@ -118,6 +118,20 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 	}
 
 	write_sysreg(val, cptr_el2);
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * configured and enabled. We can now restore the guest's S1
+		 * configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
 }
 
 static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
@@ -159,6 +173,23 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		u64 val;
+
+		/*
+		 * Set the TCR and SCTLR registers in the exact opposite
+		 * sequence as __activate_traps_nvhe (first prevent walks,
+		 * then force the MMU on). A generous sprinkling of isb()
+		 * ensure that things happen in this exact order.
+		 */
+		val = read_sysreg_el1(SYS_TCR);
+		write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
+		isb();
+		val = read_sysreg_el1(SYS_SCTLR);
+		write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
+		isb();
+	}
+
 	__deactivate_traps_common();
 
 	mdcr_el2 &= MDCR_EL2_HPMN_MASK;
@@ -657,7 +688,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 	 */
 	if (system_uses_irq_prio_masking()) {
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
-		dsb(sy);
+		pmr_sync();
 	}
 
 	vcpu = kern_hyp_va(vcpu);
@@ -670,18 +701,23 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 
 	__sysreg_save_state_nvhe(host_ctxt);
 
-	__activate_vm(kern_hyp_va(vcpu->kvm));
-	__activate_traps(vcpu);
-
-	__hyp_vgic_restore_state(vcpu);
-	__timer_enable_traps(vcpu);
-
 	/*
 	 * We must restore the 32-bit state before the sysregs, thanks
 	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+	 *
+	 * Also, and in order to be able to deal with erratum #1319537 (A57)
+	 * and #1319367 (A72), we must ensure that all VM-related sysreg are
+	 * restored before we enable S2 translation.
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_state_nvhe(guest_ctxt);
+
+	__activate_vm(kern_hyp_va(vcpu->kvm));
+	__activate_traps(vcpu);
+
+	__hyp_vgic_restore_state(vcpu);
+	__timer_enable_traps(vcpu);
+
 	__debug_switch_to_guest(vcpu);
 
 	__set_guest_arch_workaround_state(vcpu);
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 7ddbc849b580..22b8128d19f6 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -117,12 +117,26 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
-	write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+
+	if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	} else	if (!ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for guest registers, hence the context
+		 * test. We're coming from the host, so SCTLR.M is already
+		 * set. Pairs with __activate_traps_nvhe().
+		 */
+		write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
+				  TCR_EPD1_MASK | TCR_EPD0_MASK),
+				 SYS_TCR);
+		isb();
+	}
+
 	write_sysreg(ctxt->sys_regs[ACTLR_EL1],		actlr_el1);
 	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	SYS_CPACR);
 	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	SYS_TTBR0);
 	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	SYS_TTBR1);
-	write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
 	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	SYS_ESR);
 	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	SYS_AFSR0);
 	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	SYS_AFSR1);
@@ -135,6 +149,23 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367) &&
+	    ctxt->__hyp_running_vcpu) {
+		/*
+		 * Must only be done for host registers, hence the context
+		 * test. Pairs with __deactivate_traps_nvhe().
+		 */
+		isb();
+		/*
+		 * At this stage, and thanks to the above isb(), S2 is
+		 * deconfigured and disabled. We can now restore the host's
+		 * S1 configuration: SCTLR, and only then TCR.
+		 */
+		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
+		isb();
+		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
+	}
+
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
 	write_sysreg_el1(ctxt->gp_regs.elr_el1,		SYS_ELR);
 	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index eb0efc5557f3..c2bc17ca6430 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -63,6 +63,22 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 						  struct tlb_inv_context *cxt)
 {
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		u64 val;
+
+		/*
+		 * For CPUs that are affected by ARM 1319367, we need to
+		 * avoid a host Stage-1 walk while we have the guest's
+		 * VMID set in the VTTBR in order to invalidate TLBs.
+		 * We're guaranteed that the S1 MMU is enabled, so we can
+		 * simply set the EPD bits to avoid any further TLB fill.
+		 */
+		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
+		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
+		write_sysreg_el1(val, SYS_TCR);
+		isb();
+	}
+
 	__load_guest_stage2(kvm);
 	isb();
 }
@@ -100,6 +116,13 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 						 struct tlb_inv_context *cxt)
 {
 	write_sysreg(0, vttbr_el2);
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) {
+		/* Ensure write of the host VMID */
+		isb();
+		/* Restore the host's TCR_EL1 */
+		write_sysreg_el1(cxt->tcr, SYS_TCR);
+	}
 }
 
 static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,