Merge tag 'kvmarm-5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for Linux 5.12

- Make the nVHE EL2 object relocatable, resulting in much more
  maintainable code
- Handle concurrent translation faults hitting the same page
  in a more elegant way
- Support for the standard TRNG hypervisor call
- A bunch of small PMU/Debug fixes
- Allow the disabling of symbol export from assembly code
- Simplification of the early init hypercall handling

9 files changed, 62 insertions, 80 deletions

diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 015ddffaf6ca..b56a4b2bc248 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -17,7 +17,7 @@
 #include <asm/lse.h>
 
 #define ATOMIC_OP(op)							\
-static inline void arch_##op(int i, atomic_t *v)			\
+static __always_inline void arch_##op(int i, atomic_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub)
 #undef ATOMIC_OP
 
 #define ATOMIC_FETCH_OP(name, op)					\
-static inline int arch_##op##name(int i, atomic_t *v)			\
+static __always_inline int arch_##op##name(int i, atomic_t *v)		\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return)
 #undef ATOMIC_FETCH_OPS
 
 #define ATOMIC64_OP(op)							\
-static inline void arch_##op(long i, atomic64_t *v)			\
+static __always_inline void arch_##op(long i, atomic64_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub)
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, op)					\
-static inline long arch_##op##name(long i, atomic64_t *v)		\
+static __always_inline long arch_##op##name(long i, atomic64_t *v)	\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return)
 #undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_FETCH_OPS
 
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }
diff --git a/arch/arm64/include/asm/hyp_image.h b/arch/arm64/include/asm/hyp_image.h
index daa1a1da539e..737ded6b6d0d 100644
--- a/arch/arm64/include/asm/hyp_image.h
+++ b/arch/arm64/include/asm/hyp_image.h
@@ -7,6 +7,9 @@
 #ifndef __ARM64_HYP_IMAGE_H__
 #define __ARM64_HYP_IMAGE_H__
 
+#define __HYP_CONCAT(a, b)	a ## b
+#define HYP_CONCAT(a, b)	__HYP_CONCAT(a, b)
+
 /*
  * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_,
  * to separate it from the kernel proper.
@@ -21,9 +24,31 @@
  */
 #define HYP_SECTION_NAME(NAME)	.hyp##NAME
 
+/* Symbol defined at the beginning of each hyp section. */
+#define HYP_SECTION_SYMBOL_NAME(NAME) \
+	HYP_CONCAT(__hyp_section_, HYP_SECTION_NAME(NAME))
+
+/*
+ * Helper to generate linker script statements starting a hyp section.
+ *
+ * A symbol with a well-known name is defined at the first byte. This
+ * is used as a base for hyp relocations (see gen-hyprel.c). It must
+ * be defined inside the section so the linker of `vmlinux` cannot
+ * separate it from the section data.
+ */
+#define BEGIN_HYP_SECTION(NAME)				\
+	HYP_SECTION_NAME(NAME) : {			\
+		HYP_SECTION_SYMBOL_NAME(NAME) = .;
+
+/* Helper to generate linker script statements ending a hyp section. */
+#define END_HYP_SECTION					\
+	}
+
 /* Defines an ELF hyp section from input section @NAME and its subsections. */
-#define HYP_SECTION(NAME) \
-	HYP_SECTION_NAME(NAME) : { *(NAME NAME##.*) }
+#define HYP_SECTION(NAME)			\
+	BEGIN_HYP_SECTION(NAME)			\
+		*(NAME NAME##.*)		\
+	END_HYP_SECTION
 
 /*
  * Defines a linker script alias of a kernel-proper symbol referenced by
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 8a33d83ea843..22d933e9b59e 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -199,32 +199,6 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
-#if defined(GCC_VERSION) && GCC_VERSION < 50000
-#define SYM_CONSTRAINT	"i"
-#else
-#define SYM_CONSTRAINT	"S"
-#endif
-
-/*
- * Obtain the PC-relative address of a kernel symbol
- * s: symbol
- *
- * The goal of this macro is to return a symbol's address based on a
- * PC-relative computation, as opposed to a loading the VA from a
- * constant pool or something similar. This works well for HYP, as an
- * absolute VA is guaranteed to be wrong. Only use this if trying to
- * obtain the address of a symbol (i.e. not something you obtained by
- * following a pointer).
- */
-#define hyp_symbol_addr(s)						\
-	({								\
-		typeof(s) *addr;					\
-		asm("adrp	%0, %1\n"				\
-		    "add	%0, %0, :lo12:%1\n"			\
-		    : "=r" (addr) : SYM_CONSTRAINT (&s));		\
-		addr;							\
-	})
-
 #define __KVM_EXTABLE(from, to)						\
 	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
 	"	.align		3\n"					\
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 1b8a3d825276..3d10e6527f7d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -770,4 +770,6 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_vcpu_has_pmu(vcpu)					\
 	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
 
+int kvm_trng_call(struct kvm_vcpu *vcpu);
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index e52d82aeadca..90873851f677 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -73,49 +73,39 @@ alternative_cb_end
 .endm
 
 /*
- * Convert a kernel image address to a PA
- * reg: kernel address to be converted in place
+ * Convert a hypervisor VA to a PA
+ * reg: hypervisor address to be converted in place
  * tmp: temporary register
- *
- * The actual code generation takes place in kvm_get_kimage_voffset, and
- * the instructions below are only there to reserve the space and
- * perform the register allocation (kvm_get_kimage_voffset uses the
- * specific registers encoded in the instructions).
  */
-.macro kimg_pa reg, tmp
-alternative_cb kvm_get_kimage_voffset
-	movz	\tmp, #0
-	movk	\tmp, #0, lsl #16
-	movk	\tmp, #0, lsl #32
-	movk	\tmp, #0, lsl #48
-alternative_cb_end
-
-	/* reg = __pa(reg) */
-	sub	\reg, \reg, \tmp
+.macro hyp_pa reg, tmp
+	ldr_l	\tmp, hyp_physvirt_offset
+	add	\reg, \reg, \tmp
 .endm
 
 /*
- * Convert a kernel image address to a hyp VA
- * reg: kernel address to be converted in place
+ * Convert a hypervisor VA to a kernel image address
+ * reg: hypervisor address to be converted in place
  * tmp: temporary register
  *
  * The actual code generation takes place in kvm_get_kimage_voffset, and
  * the instructions below are only there to reserve the space and
- * perform the register allocation (kvm_update_kimg_phys_offset uses the
+ * perform the register allocation (kvm_get_kimage_voffset uses the
  * specific registers encoded in the instructions).
  */
-.macro kimg_hyp_va reg, tmp
-alternative_cb kvm_update_kimg_phys_offset
+.macro hyp_kimg_va reg, tmp
+	/* Convert hyp VA -> PA. */
+	hyp_pa	\reg, \tmp
+
+	/* Load kimage_voffset. */
+alternative_cb kvm_get_kimage_voffset
 	movz	\tmp, #0
 	movk	\tmp, #0, lsl #16
 	movk	\tmp, #0, lsl #32
 	movk	\tmp, #0, lsl #48
 alternative_cb_end
 
-	sub	\reg, \reg, \tmp
-	mov_q	\tmp, PAGE_OFFSET
-	orr	\reg, \reg, \tmp
-	kern_hyp_va \reg
+	/* Convert PA -> kimg VA. */
+	add	\reg, \reg, \tmp
 .endm
 
 #else
@@ -129,6 +119,7 @@ alternative_cb_end
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
 void kvm_compute_layout(void);
+void kvm_apply_hyp_relocations(void);
 
 static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 {
@@ -144,24 +135,6 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 
 #define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))
 
-static __always_inline unsigned long __kimg_hyp_va(unsigned long v)
-{
-	unsigned long offset;
-
-	asm volatile(ALTERNATIVE_CB("movz %0, #0\n"
-				    "movk %0, #0, lsl #16\n"
-				    "movk %0, #0, lsl #32\n"
-				    "movk %0, #0, lsl #48\n",
-				    kvm_update_kimg_phys_offset)
-		     : "=r" (offset));
-
-	return __kern_hyp_va((v - offset) | PAGE_OFFSET);
-}
-
-#define kimg_fn_hyp_va(v) 	((typeof(*v))(__kimg_hyp_va((unsigned long)(v))))
-
-#define kimg_fn_ptr(x)	(typeof(x) **)(x)
-
 /*
  * We currently support using a VM-specified IPA size. For backward
  * compatibility, the default IPA size is fixed to 40bits.
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 52ab38db04c7..8886d43cfb11 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -157,6 +157,11 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  * If device attributes are not explicitly requested in @prot, then the
  * mapping will be normal, cacheable.
  *
+ * Note that the update of a valid leaf PTE in this function will be aborted,
+ * if it's trying to recreate the exact same mapping or only change the access
+ * permissions. Instead, the vCPU will exit one more time from guest if still
+ * needed and then go through the path of relaxing permissions.
+ *
  * Note that this function will both coalesce existing table entries and split
  * existing block mappings, relying on page-faults to fault back areas outside
  * of the new mapping lazily.
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 69ad25fbeae4..ca2cd75d3286 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -94,8 +94,7 @@
 #endif /* CONFIG_ARM64_FORCE_52BIT */
 
 extern phys_addr_t arm64_dma_phys_limit;
-extern phys_addr_t arm64_dma32_phys_limit;
-#define ARCH_LOW_ADDRESS_LIMIT	((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
+#define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
 
 struct debug_info {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 8ff579361731..2f36b16a5b5d 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -11,7 +11,8 @@ extern char __alt_instructions[], __alt_instructions_end[];
 extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
 extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
 extern char __hyp_text_start[], __hyp_text_end[];
-extern char __hyp_data_ro_after_init_start[], __hyp_data_ro_after_init_end[];
+extern char __hyp_rodata_start[], __hyp_rodata_end[];
+extern char __hyp_reloc_begin[], __hyp_reloc_end[];
 extern char __idmap_text_start[], __idmap_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __inittext_begin[], __inittext_end[];
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 8b5e7e5c3cc8..2fb3f386588c 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -846,7 +846,10 @@
 
 #define ID_DFR0_PERFMON_SHIFT		24
 
+#define ID_DFR0_PERFMON_8_0		0x3
 #define ID_DFR0_PERFMON_8_1		0x4
+#define ID_DFR0_PERFMON_8_4		0x5
+#define ID_DFR0_PERFMON_8_5		0x6
 
 #define ID_ISAR4_SWP_FRAC_SHIFT		28
 #define ID_ISAR4_PSR_M_SHIFT		24