Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Several cases of bug fixes in 'net' overlapping other changes in
'net-next-.

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 77 insertions, 12 deletions

diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index d7ea6bcb29bf..8ef05381984b 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -66,6 +66,7 @@ extern char __kvm_hyp_vector[];
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
+extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 2d19e02d03fd..d5423ab15ed5 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -57,6 +57,9 @@ struct kvm_arch {
 	/* VTTBR value associated with below pgd and vmid */
 	u64    vttbr;
 
+	/* The last vcpu id that ran on each physical CPU */
+	int __percpu *last_vcpu_ran;
+
 	/* Timer */
 	struct arch_timer_kvm	timer;
 
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index 343135ede5fa..58508900c4bb 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -71,6 +71,7 @@
 #define ICIALLUIS	__ACCESS_CP15(c7, 0, c1, 0)
 #define ATS1CPR		__ACCESS_CP15(c7, 0, c8, 0)
 #define TLBIALLIS	__ACCESS_CP15(c8, 0, c3, 0)
+#define TLBIALL		__ACCESS_CP15(c8, 0, c7, 0)
 #define TLBIALLNSNHIS	__ACCESS_CP15(c8, 4, c3, 4)
 #define PRRR		__ACCESS_CP15(c10, 0, c2, 0)
 #define NMRR		__ACCESS_CP15(c10, 0, c2, 1)
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 194b69923389..ada0d29a660f 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -19,7 +19,7 @@
  * This may need to be greater than __NR_last_syscall+1 in order to
  * account for the padding in the syscall table
  */
-#define __NR_syscalls  (396)
+#define __NR_syscalls  (400)
 
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 2cb9dc770e1d..314100a06ccb 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -420,6 +420,9 @@
 #define __NR_copy_file_range		(__NR_SYSCALL_BASE+391)
 #define __NR_preadv2			(__NR_SYSCALL_BASE+392)
 #define __NR_pwritev2			(__NR_SYSCALL_BASE+393)
+#define __NR_pkey_mprotect		(__NR_SYSCALL_BASE+394)
+#define __NR_pkey_alloc			(__NR_SYSCALL_BASE+395)
+#define __NR_pkey_free			(__NR_SYSCALL_BASE+396)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 703fa0f3cd8f..08030b18f10a 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -403,6 +403,9 @@
 		CALL(sys_copy_file_range)
 		CALL(sys_preadv2)
 		CALL(sys_pwritev2)
+		CALL(sys_pkey_mprotect)
+/* 395 */	CALL(sys_pkey_alloc)
+		CALL(sys_pkey_free)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 08bb84f2ad58..19b5f5c1c0ff 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -114,11 +114,18 @@ void kvm_arch_check_processor_compat(void *rtn)
  */
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	int ret = 0;
+	int ret, cpu;
 
 	if (type)
 		return -EINVAL;
 
+	kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
+	if (!kvm->arch.last_vcpu_ran)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1;
+
 	ret = kvm_alloc_stage2_pgd(kvm);
 	if (ret)
 		goto out_fail_alloc;
@@ -141,6 +148,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 out_free_stage2_pgd:
 	kvm_free_stage2_pgd(kvm);
 out_fail_alloc:
+	free_percpu(kvm->arch.last_vcpu_ran);
+	kvm->arch.last_vcpu_ran = NULL;
 	return ret;
 }
 
@@ -168,6 +177,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	int i;
 
+	free_percpu(kvm->arch.last_vcpu_ran);
+	kvm->arch.last_vcpu_ran = NULL;
+
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
 			kvm_arch_vcpu_free(kvm->vcpus[i]);
@@ -312,6 +324,19 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	int *last_ran;
+
+	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+
+	/*
+	 * We might get preempted before the vCPU actually runs, but
+	 * over-invalidation doesn't affect correctness.
+	 */
+	if (*last_ran != vcpu->vcpu_id) {
+		kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu);
+		*last_ran = vcpu->vcpu_id;
+	}
+
 	vcpu->cpu = cpu;
 	vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
 
diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c
index 729652854f90..6d810af2d9fd 100644
--- a/arch/arm/kvm/hyp/tlb.c
+++ b/arch/arm/kvm/hyp/tlb.c
@@ -55,6 +55,21 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	__kvm_tlb_flush_vmid(kvm);
 }
 
+void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
+
+	/* Switch to requested VMID */
+	write_sysreg(kvm->arch.vttbr, VTTBR);
+	isb();
+
+	write_sysreg(0, TLBIALL);
+	dsb(nsh);
+	isb();
+
+	write_sysreg(0, VTTBR);
+}
+
 void __hyp_text __kvm_flush_vm_context(void)
 {
 	write_sysreg(0, TLBIALLNSNHIS);
diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S
index 6d8e8e3365d1..4cdfab31a0b6 100644
--- a/arch/arm/mm/abort-lv4t.S
+++ b/arch/arm/mm/abort-lv4t.S
@@ -7,7 +7,7 @@
  *	   : r4 = aborted context pc
  *	   : r5 = aborted context psr
  *
- * Returns : r4-r5, r10-r11, r13 preserved
+ * Returns : r4-r5, r9-r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  * Note: we read user space.  This means we might cause a data
@@ -48,7 +48,10 @@ ENTRY(v4t_late_abort)
 /* c */	b	do_DataAbort			@ ldc	rd, [rn], #m	@ Same as ldr	rd, [rn], #m
 /* d */	b	do_DataAbort			@ ldc	rd, [rn, #m]
 /* e */	b	.data_unknown
-/* f */
+/* f */	b	.data_unknown
+
+.data_unknown_r9:
+	ldr	r9, [sp], #4
 .data_unknown:	@ Part of jumptable
 	mov	r0, r4
 	mov	r1, r8
@@ -57,6 +60,7 @@ ENTRY(v4t_late_abort)
 .data_arm_ldmstm:
 	tst	r8, #1 << 21			@ check writeback bit
 	beq	do_DataAbort			@ no writeback -> no fixup
+	str	r9, [sp, #-4]!
 	mov	r7, #0x11
 	orr	r7, r7, #0x1100
 	and	r6, r8, r7
@@ -75,12 +79,14 @@ ENTRY(v4t_late_abort)
 	subne	r7, r7, r6, lsl #2		@ Undo increment
 	addeq	r7, r7, r6, lsl #2		@ Undo decrement
 	str	r7, [r2, r9, lsr #14]		@ Put register 'Rn'
+	ldr	r9, [sp], #4
 	b	do_DataAbort
 
 .data_arm_lateldrhpre:
 	tst	r8, #1 << 21			@ Check writeback bit
 	beq	do_DataAbort			@ No writeback -> no fixup
 .data_arm_lateldrhpost:
+	str	r9, [sp, #-4]!
 	and	r9, r8, #0x00f			@ get Rm / low nibble of immediate value
 	tst	r8, #1 << 22			@ if (immediate offset)
 	andne	r6, r8, #0xf00			@ { immediate high nibble
@@ -93,6 +99,7 @@ ENTRY(v4t_late_abort)
 	subne	r7, r7, r6			@ Undo incrmenet
 	addeq	r7, r7, r6			@ Undo decrement
 	str	r7, [r2, r9, lsr #14]		@ Put register 'Rn'
+	ldr	r9, [sp], #4
 	b	do_DataAbort
 
 .data_arm_lateldrpreconst:
@@ -101,12 +108,14 @@ ENTRY(v4t_late_abort)
 .data_arm_lateldrpostconst:
 	movs	r6, r8, lsl #20			@ Get offset
 	beq	do_DataAbort			@ zero -> no fixup
+	str	r9, [sp, #-4]!
 	and	r9, r8, #15 << 16		@ Extract 'n' from instruction
 	ldr	r7, [r2, r9, lsr #14]		@ Get register 'Rn'
 	tst	r8, #1 << 23			@ Check U bit
 	subne	r7, r7, r6, lsr #20		@ Undo increment
 	addeq	r7, r7, r6, lsr #20		@ Undo decrement
 	str	r7, [r2, r9, lsr #14]		@ Put register 'Rn'
+	ldr	r9, [sp], #4
 	b	do_DataAbort
 
 .data_arm_lateldrprereg:
@@ -115,6 +124,7 @@ ENTRY(v4t_late_abort)
 .data_arm_lateldrpostreg:
 	and	r7, r8, #15			@ Extract 'm' from instruction
 	ldr	r6, [r2, r7, lsl #2]		@ Get register 'Rm'
+	str	r9, [sp, #-4]!
 	mov	r9, r8, lsr #7			@ get shift count
 	ands	r9, r9, #31
 	and	r7, r8, #0x70			@ get shift type
@@ -126,33 +136,33 @@ ENTRY(v4t_late_abort)
 	b	.data_arm_apply_r6_and_rn
 	b	.data_arm_apply_r6_and_rn	@ 1: LSL #0
 	nop
-	b	.data_unknown			@ 2: MUL?
+	b	.data_unknown_r9		@ 2: MUL?
 	nop
-	b	.data_unknown			@ 3: MUL?
+	b	.data_unknown_r9		@ 3: MUL?
 	nop
 	mov	r6, r6, lsr r9			@ 4: LSR #!0
 	b	.data_arm_apply_r6_and_rn
 	mov	r6, r6, lsr #32			@ 5: LSR #32
 	b	.data_arm_apply_r6_and_rn
-	b	.data_unknown			@ 6: MUL?
+	b	.data_unknown_r9		@ 6: MUL?
 	nop
-	b	.data_unknown			@ 7: MUL?
+	b	.data_unknown_r9		@ 7: MUL?
 	nop
 	mov	r6, r6, asr r9			@ 8: ASR #!0
 	b	.data_arm_apply_r6_and_rn
 	mov	r6, r6, asr #32			@ 9: ASR #32
 	b	.data_arm_apply_r6_and_rn
-	b	.data_unknown			@ A: MUL?
+	b	.data_unknown_r9		@ A: MUL?
 	nop
-	b	.data_unknown			@ B: MUL?
+	b	.data_unknown_r9		@ B: MUL?
 	nop
 	mov	r6, r6, ror r9			@ C: ROR #!0
 	b	.data_arm_apply_r6_and_rn
 	mov	r6, r6, rrx			@ D: RRX
 	b	.data_arm_apply_r6_and_rn
-	b	.data_unknown			@ E: MUL?
+	b	.data_unknown_r9		@ E: MUL?
 	nop
-	b	.data_unknown			@ F: MUL?
+	b	.data_unknown_r9		@ F: MUL?
 
 .data_thumb_abort:
 	ldrh	r8, [r4]			@ read instruction
@@ -190,6 +200,7 @@ ENTRY(v4t_late_abort)
 .data_thumb_pushpop:
 	tst	r8, #1 << 10
 	beq	.data_unknown
+	str	r9, [sp, #-4]!
 	and	r6, r8, #0x55			@ hweight8(r8) + R bit
 	and	r9, r8, #0xaa
 	add	r6, r6, r9, lsr #1
@@ -204,9 +215,11 @@ ENTRY(v4t_late_abort)
 	addeq	r7, r7, r6, lsl #2		@ increment SP if PUSH
 	subne	r7, r7, r6, lsl #2		@ decrement SP if POP
 	str	r7, [r2, #13 << 2]
+	ldr	r9, [sp], #4
 	b	do_DataAbort
 
 .data_thumb_ldmstm:
+	str	r9, [sp, #-4]!
 	and	r6, r8, #0x55			@ hweight8(r8)
 	and	r9, r8, #0xaa
 	add	r6, r6, r9, lsr #1
@@ -219,4 +232,5 @@ ENTRY(v4t_late_abort)
 	and	r6, r6, #15			@ number of regs to transfer
 	sub	r7, r7, r6, lsl #2		@ always decrement
 	str	r7, [r2, r9, lsr #6]
+	ldr	r9, [sp], #4
 	b	do_DataAbort