Merge 4.4-rc5 into usb-next as we want those fixes here for testing

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

10 files changed, 129 insertions, 96 deletions

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index e81cd48d6245..925552e7b4f3 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -269,6 +269,7 @@
 			clock-frequency = <0>;	/* Updated by bootloader */
 			voltage-ranges = <1800 1800 3300 3300>;
 			sdhci,auto-cmd12;
+			little-endian;
 			bus-width = <4>;
 		};
 
@@ -277,6 +278,7 @@
 			reg = <0x0 0x2300000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -287,6 +289,7 @@
 			reg = <0x0 0x2310000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -297,6 +300,7 @@
 			reg = <0x0 0x2320000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -307,6 +311,7 @@
 			reg = <0x0 0x2330000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 030cdcb46c6b..2731d3b25ed2 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -77,6 +77,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/stringify.h>
+#include <asm/barrier.h>
 
 /*
  * Low-level accessors
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 3ca894ecf699..25a40213bd9b 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -100,13 +100,21 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 }
 
 /*
- * vcpu_reg should always be passed a register number coming from a
- * read of ESR_EL2. Otherwise, it may give the wrong result on AArch32
- * with banked registers.
+ * vcpu_get_reg and vcpu_set_reg should always be passed a register number
+ * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on
+ * AArch32 with banked registers.
  */
-static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num)
+static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
+					 u8 reg_num)
 {
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+}
+
+static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+				unsigned long val)
+{
+	if (reg_num != 31)
+		vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val;
 }
 
 /* Get vcpu SPSR for current mode */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7e074f93f383..63f52b55defe 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -276,10 +276,14 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
-	    pte_valid(*ptep)) {
-		BUG_ON(!pte_young(pte));
-		BUG_ON(pte_write(*ptep) && !pte_dirty(pte));
+	if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
+	    pte_valid(*ptep) && pte_valid(pte)) {
+		VM_WARN_ONCE(!pte_young(pte),
+			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
+		VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte),
+			     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
 	}
 
 	set_pte(ptep, pte);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 1ee2c3937d4e..71426a78db12 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -5,6 +5,7 @@
  */
 
 #include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
@@ -140,7 +141,7 @@ SECTIONS
 		ARM_EXIT_KEEP(EXIT_DATA)
 	}
 
-	PERCPU_SECTION(64)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
@@ -158,7 +159,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	_data = .;
 	_sdata = .;
-	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	PECOFF_EDATA_PADDING
 	_edata = .;
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 68a0759b1375..15f0477b0d2a 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -37,7 +37,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int ret;
 
-	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0),
 			    kvm_vcpu_hvc_get_imm(vcpu));
 
 	ret = kvm_psci_call(vcpu);
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 87a64e8db04c..d2650e84faf2 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -78,7 +78,7 @@ static u32 get_ccsidr(u32 csselr)
  * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
  */
 static bool access_dcsw(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (!p->is_write)
@@ -94,21 +94,19 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
  * sys_regs and leave it in complete control of the caches.
  */
 static bool access_vm_reg(struct kvm_vcpu *vcpu,
-			  const struct sys_reg_params *p,
+			  struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	unsigned long val;
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
 
 	BUG_ON(!p->is_write);
 
-	val = *vcpu_reg(vcpu, p->Rt);
 	if (!p->is_aarch32) {
-		vcpu_sys_reg(vcpu, r->reg) = val;
+		vcpu_sys_reg(vcpu, r->reg) = p->regval;
 	} else {
 		if (!p->is_32bit)
-			vcpu_cp15_64_high(vcpu, r->reg) = val >> 32;
-		vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
+			vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval);
+		vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval);
 	}
 
 	kvm_toggle_cache(vcpu, was_enabled);
@@ -122,22 +120,19 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
  * for both AArch64 and AArch32 accesses.
  */
 static bool access_gic_sgi(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *p,
+			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
-	u64 val;
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p);
 
-	val = *vcpu_reg(vcpu, p->Rt);
-	vgic_v3_dispatch_sgi(vcpu, val);
+	vgic_v3_dispatch_sgi(vcpu, p->regval);
 
 	return true;
 }
 
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (p->is_write)
@@ -147,19 +142,19 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 }
 
 static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *p,
+			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
 		return ignore_write(vcpu, p);
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = (1 << 3);
+		p->regval = (1 << 3);
 		return true;
 	}
 }
 
 static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
-				   const struct sys_reg_params *p,
+				   struct sys_reg_params *p,
 				   const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
@@ -167,7 +162,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
 	} else {
 		u32 val;
 		asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
-		*vcpu_reg(vcpu, p->Rt) = val;
+		p->regval = val;
 		return true;
 	}
 }
@@ -200,17 +195,17 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
  *   now use the debug registers.
  */
 static bool trap_debug_regs(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
-		vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu_sys_reg(vcpu, r->reg) = p->regval;
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+		p->regval = vcpu_sys_reg(vcpu, r->reg);
 	}
 
-	trace_trap_reg(__func__, r->reg, p->is_write, *vcpu_reg(vcpu, p->Rt));
+	trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
 
 	return true;
 }
@@ -225,10 +220,10 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
  * hyp.S code switches between host and guest values in future.
  */
 static inline void reg_to_dbg(struct kvm_vcpu *vcpu,
-			      const struct sys_reg_params *p,
+			      struct sys_reg_params *p,
 			      u64 *dbg_reg)
 {
-	u64 val = *vcpu_reg(vcpu, p->Rt);
+	u64 val = p->regval;
 
 	if (p->is_32bit) {
 		val &= 0xffffffffUL;
@@ -240,19 +235,16 @@ static inline void reg_to_dbg(struct kvm_vcpu *vcpu,
 }
 
 static inline void dbg_to_reg(struct kvm_vcpu *vcpu,
-			      const struct sys_reg_params *p,
+			      struct sys_reg_params *p,
 			      u64 *dbg_reg)
 {
-	u64 val = *dbg_reg;
-
+	p->regval = *dbg_reg;
 	if (p->is_32bit)
-		val &= 0xffffffffUL;
-
-	*vcpu_reg(vcpu, p->Rt) = val;
+		p->regval &= 0xffffffffUL;
 }
 
 static inline bool trap_bvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
@@ -294,7 +286,7 @@ static inline void reset_bvr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_bcr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
@@ -337,7 +329,7 @@ static inline void reset_bcr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_wvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
@@ -380,7 +372,7 @@ static inline void reset_wvr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_wcr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
@@ -687,7 +679,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
@@ -697,23 +689,23 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu,
 		u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1);
 		u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT);
 
-		*vcpu_reg(vcpu, p->Rt) = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
-					  (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
-					  (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) |
-					  (6 << 16) | (el3 << 14) | (el3 << 12));
+		p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
+			     (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
+			     (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20)
+			     | (6 << 16) | (el3 << 14) | (el3 << 12));
 		return true;
 	}
 }
 
 static bool trap_debug32(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *p,
+			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
-		vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu_cp14(vcpu, r->reg) = p->regval;
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+		p->regval = vcpu_cp14(vcpu, r->reg);
 	}
 
 	return true;
@@ -731,7 +723,7 @@ static bool trap_debug32(struct kvm_vcpu *vcpu,
  */
 
 static inline bool trap_xvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
@@ -740,12 +732,12 @@ static inline bool trap_xvr(struct kvm_vcpu *vcpu,
 		u64 val = *dbg_reg;
 
 		val &= 0xffffffffUL;
-		val |= *vcpu_reg(vcpu, p->Rt) << 32;
+		val |= p->regval << 32;
 		*dbg_reg = val;
 
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = *dbg_reg >> 32;
+		p->regval = *dbg_reg >> 32;
 	}
 
 	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
@@ -991,7 +983,7 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * Return 0 if the access has been handled, and -1 if not.
  */
 static int emulate_cp(struct kvm_vcpu *vcpu,
-		      const struct sys_reg_params *params,
+		      struct sys_reg_params *params,
 		      const struct sys_reg_desc *table,
 		      size_t num)
 {
@@ -1062,12 +1054,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	int Rt = (hsr >> 5) & 0xf;
 	int Rt2 = (hsr >> 10) & 0xf;
 
 	params.is_aarch32 = true;
 	params.is_32bit = false;
 	params.CRm = (hsr >> 1) & 0xf;
-	params.Rt = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
 
 	params.Op0 = 0;
@@ -1076,15 +1068,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 	params.CRn = 0;
 
 	/*
-	 * Massive hack here. Store Rt2 in the top 32bits so we only
-	 * have one register to deal with. As we use the same trap
+	 * Make a 64-bit value out of Rt and Rt2. As we use the same trap
 	 * backends between AArch32 and AArch64, we get away with it.
 	 */
 	if (params.is_write) {
-		u64 val = *vcpu_reg(vcpu, params.Rt);
-		val &= 0xffffffff;
-		val |= *vcpu_reg(vcpu, Rt2) << 32;
-		*vcpu_reg(vcpu, params.Rt) = val;
+		params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff;
+		params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
 	}
 
 	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
@@ -1095,11 +1084,10 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 	unhandled_cp_access(vcpu, &params);
 
 out:
-	/* Do the opposite hack for the read side */
+	/* Split up the value between registers for the read side */
 	if (!params.is_write) {
-		u64 val = *vcpu_reg(vcpu, params.Rt);
-		val >>= 32;
-		*vcpu_reg(vcpu, Rt2) = val;
+		vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
+		vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
 	}
 
 	return 1;
@@ -1118,21 +1106,24 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	int Rt  = (hsr >> 5) & 0xf;
 
 	params.is_aarch32 = true;
 	params.is_32bit = true;
 	params.CRm = (hsr >> 1) & 0xf;
-	params.Rt  = (hsr >> 5) & 0xf;
+	params.regval = vcpu_get_reg(vcpu, Rt);
 	params.is_write = ((hsr & 1) == 0);
 	params.CRn = (hsr >> 10) & 0xf;
 	params.Op0 = 0;
 	params.Op1 = (hsr >> 14) & 0x7;
 	params.Op2 = (hsr >> 17) & 0x7;
 
-	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
-		return 1;
-	if (!emulate_cp(vcpu, &params, global, nr_global))
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
+	    !emulate_cp(vcpu, &params, global, nr_global)) {
+		if (!params.is_write)
+			vcpu_set_reg(vcpu, Rt, params.regval);
 		return 1;
+	}
 
 	unhandled_cp_access(vcpu, &params);
 	return 1;
@@ -1175,7 +1166,7 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 }
 
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *params)
+			   struct sys_reg_params *params)
 {
 	size_t num;
 	const struct sys_reg_desc *table, *r;
@@ -1230,6 +1221,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct sys_reg_params params;
 	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
+	int Rt = (esr >> 5) & 0x1f;
+	int ret;
 
 	trace_kvm_handle_sys_reg(esr);
 
@@ -1240,10 +1233,14 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.CRn = (esr >> 10) & 0xf;
 	params.CRm = (esr >> 1) & 0xf;
 	params.Op2 = (esr >> 17) & 0x7;
-	params.Rt = (esr >> 5) & 0x1f;
+	params.regval = vcpu_get_reg(vcpu, Rt);
 	params.is_write = !(esr & 1);
 
-	return emulate_sys_reg(vcpu, &params);
+	ret = emulate_sys_reg(vcpu, &params);
+
+	if (!params.is_write)
+		vcpu_set_reg(vcpu, Rt, params.regval);
+	return ret;
 }
 
 /******************************************************************************
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index eaa324e4db4d..dbbb01cfbee9 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -28,7 +28,7 @@ struct sys_reg_params {
 	u8	CRn;
 	u8	CRm;
 	u8	Op2;
-	u8	Rt;
+	u64	regval;
 	bool	is_write;
 	bool	is_aarch32;
 	bool	is_32bit;	/* Only valid if is_aarch32 is true */
@@ -44,7 +44,7 @@ struct sys_reg_desc {
 
 	/* Trapped access from guest, if non-NULL. */
 	bool (*access)(struct kvm_vcpu *,
-		       const struct sys_reg_params *,
+		       struct sys_reg_params *,
 		       const struct sys_reg_desc *);
 
 	/* Initialization for vcpu. */
@@ -77,9 +77,9 @@ static inline bool ignore_write(struct kvm_vcpu *vcpu,
 }
 
 static inline bool read_zero(struct kvm_vcpu *vcpu,
-			     const struct sys_reg_params *p)
+			     struct sys_reg_params *p)
 {
-	*vcpu_reg(vcpu, p->Rt) = 0;
+	p->regval = 0;
 	return true;
 }
 
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index 1e4576824165..ed90578fa120 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -31,13 +31,13 @@
 #include "sys_regs.h"
 
 static bool access_actlr(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *p,
+			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
 {
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1);
+	p->regval = vcpu_sys_reg(vcpu, ACTLR_EL1);
 	return true;
 }
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index d6a53ef2350b..b162ad70effc 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -139,6 +139,12 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 /* Stack must be multiples of 16B */
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
+#define _STACK_SIZE \
+	(MAX_BPF_STACK \
+	 + 4 /* extra for skb_copy_bits buffer */)
+
+#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
+
 static void build_prologue(struct jit_ctx *ctx)
 {
 	const u8 r6 = bpf2a64[BPF_REG_6];
@@ -150,10 +156,6 @@ static void build_prologue(struct jit_ctx *ctx)
 	const u8 rx = bpf2a64[BPF_REG_X];
 	const u8 tmp1 = bpf2a64[TMP_REG_1];
 	const u8 tmp2 = bpf2a64[TMP_REG_2];
-	int stack_size = MAX_BPF_STACK;
-
-	stack_size += 4; /* extra for skb_copy_bits buffer */
-	stack_size = STACK_ALIGN(stack_size);
 
 	/*
 	 * BPF prog stack layout
@@ -165,12 +167,13 @@ static void build_prologue(struct jit_ctx *ctx)
 	 *                        | ... | callee saved registers
 	 *                        +-----+
 	 *                        |     | x25/x26
-	 * BPF fp register => -80:+-----+
+	 * BPF fp register => -80:+-----+ <= (BPF_FP)
 	 *                        |     |
 	 *                        | ... | BPF prog stack
 	 *                        |     |
-	 *                        |     |
-	 * current A64_SP =>      +-----+
+	 *                        +-----+ <= (BPF_FP - MAX_BPF_STACK)
+	 *                        |RSVD | JIT scratchpad
+	 * current A64_SP =>      +-----+ <= (BPF_FP - STACK_SIZE)
 	 *                        |     |
 	 *                        | ... | Function call stack
 	 *                        |     |
@@ -196,7 +199,7 @@ static void build_prologue(struct jit_ctx *ctx)
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
 	/* Set up function call stack */
-	emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx);
+	emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
 
 	/* Clear registers A and X */
 	emit_a64_mov_i64(ra, 0, ctx);
@@ -213,13 +216,9 @@ static void build_epilogue(struct jit_ctx *ctx)
 	const u8 fp = bpf2a64[BPF_REG_FP];
 	const u8 tmp1 = bpf2a64[TMP_REG_1];
 	const u8 tmp2 = bpf2a64[TMP_REG_2];
-	int stack_size = MAX_BPF_STACK;
-
-	stack_size += 4; /* extra for skb_copy_bits buffer */
-	stack_size = STACK_ALIGN(stack_size);
 
 	/* We're done with BPF stack */
-	emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx);
+	emit(A64_ADD_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
 
 	/* Restore fs (x25) and x26 */
 	emit(A64_POP(fp, A64_R(26), A64_SP), ctx);
@@ -591,7 +590,25 @@ emit_cond_jmp:
 	case BPF_ST | BPF_MEM | BPF_H:
 	case BPF_ST | BPF_MEM | BPF_B:
 	case BPF_ST | BPF_MEM | BPF_DW:
-		goto notyet;
+		/* Load imm to a register then store it */
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(1, tmp2, off, ctx);
+		emit_a64_mov_i(1, tmp, imm, ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			emit(A64_STR32(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_H:
+			emit(A64_STRH(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_B:
+			emit(A64_STRB(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_STR64(tmp, dst, tmp2), ctx);
+			break;
+		}
+		break;
 
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_W:
@@ -658,7 +675,7 @@ emit_cond_jmp:
 			return -EINVAL;
 		}
 		emit_a64_mov_i64(r3, size, ctx);
-		emit(A64_ADD_I(1, r4, fp, MAX_BPF_STACK), ctx);
+		emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx);
 		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
 		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 		emit(A64_MOV(1, A64_FP, A64_SP), ctx);