Patch queue for 3.15 - 2014-05-12

This request includes a few bug fixes that really shouldn't wait for the next
 release.
 
 It fixes KVM on 32bit PowerPC when built as module. It also fixes the PV KVM
 acceleration when NX gets honored by the host. Furthermore we fix transactional
 memory support and numa support on HV KVM.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.19 (GNU/Linux)
 
 iQIcBAABAgAGBQJTcKFaAAoJECszeR4D/txg7qYP/RX3V32i2zQYH2NpjQrDCwtY
 Wur+CQrn/VA6xhtTK1rT2zH5rNFLt6ClhtxCMkZFfBdUE4sHi3OTlEdcvXBZjbls
 JqQ/7lBkUPN8pTpz2NHP9gvH7g6v07EruysRQNa/JZMzlwhpzWk8D7yXakaCPNY/
 JZRgVTrfKnhQ8OtXt48Bp4EmEKllbNqi9kNN7dewD2dEb3fAco3Jpk6WoeG+1f0o
 jv3NmeTsp87KaRpjvDzPb7iCe6PA7GVqvJIQpir3Rpk2Kpx0yj58AfacF+f72GOf
 CPlJGepiumJCaANhV6dbvtS49vaiiAnSvbqCil2USNl0LIGWQXdSjs5lztEuiMyr
 tAav0YSVpnIcw0HJxXug/M31VwfRjYCX3hnCCIOd3Xj2jgAqwD+Lo95uUrRGJ9TP
 75zKh8E093tOXIC9CyMaiYajpFMUrCSMgnpJ+7fpeHiyigB6yc8juFxahIHsw8q1
 NgHggroJm6QNIm8JSY/tG/YET4AT7H4ZetGP8MeeRUg0TpqQXvYpkMGB8YDouaBA
 XzxjwyTq57BOYgLGExnwW3Jj0kbqVY+ts0aDGQVGrl5YFzooGqrQ61CRmwG5BvI8
 sou3l6TJ2ng8qrc7Maw9MHca1QB3mtXD7I26T/QEfQm9NLRTTqJyaxH5J1q9siRI
 PpHVE5FKnmWPNr8JlxtC
 =t2S+
 -----END PGP SIGNATURE-----

Merge tag 'signed-for-3.15' of git://github.com/agraf/linux-2.6 into kvm-master

Patch queue for 3.15 - 2014-05-12

This request includes a few bug fixes that really shouldn't wait for the next
release.

It fixes KVM on 32bit PowerPC when built as module. It also fixes the PV KVM
acceleration when NX gets honored by the host. Furthermore we fix transactional
memory support and numa support on HV KVM.

arch/powerpc/include/asm/sections.h

@@ -39,6 +39,17 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 		(unsigned long)_stext < end;
 }
 
+static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end)
+{
+#ifdef CONFIG_KVM_GUEST
+	extern char kvm_tmp[];
+	return start < (unsigned long)kvm_tmp &&
+		(unsigned long)&kvm_tmp[1024 * 1024] < end;
+#else
+	return 0;
+#endif
+}
+
 #undef dereference_function_descriptor
 static inline void *dereference_function_descriptor(void *ptr)
 {

arch/powerpc/kernel/kvm.c

@@ -74,7 +74,7 @@
 #define KVM_INST_MTSRIN		0x7c0001e4
 
 static bool kvm_patching_worked = true;
-static char kvm_tmp[1024 * 1024];
+char kvm_tmp[1024 * 1024];
 static int kvm_tmp_index;
 
 static inline void kvm_patch_ins(u32 *inst, u32 new_inst)

arch/powerpc/kvm/book3s.c

@@ -886,7 +886,7 @@ static int kvmppc_book3s_init(void)
 	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 	if (r)
 		return r;
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	r = kvmppc_book3s_init_pr();
 #endif
 	return r;
@@ -895,7 +895,7 @@ static int kvmppc_book3s_init(void)
 
 static void kvmppc_book3s_exit(void)
 {
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kvmppc_book3s_exit_pr();
 #endif
 	kvm_exit();
@@ -905,7 +905,7 @@ module_init(kvmppc_book3s_init);
 module_exit(kvmppc_book3s_exit);
 
 /* On 32bit this is our one and only kernel module */
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 MODULE_ALIAS_MISCDEV(KVM_MINOR);
 MODULE_ALIAS("devname:kvm");
 #endif

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -234,7 +234,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		pte_size = psize;
 		pte = lookup_linux_pte_and_update(pgdir, hva, writing,
 						  &pte_size);
-		if (pte_present(pte)) {
+		if (pte_present(pte) && !pte_numa(pte)) {
 			if (writing && !pte_write(pte))
 				/* make the actual HPTE be read-only */
 				ptel = hpte_make_readonly(ptel);

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1323,6 +1323,110 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mr	r3, r9
 	bl	kvmppc_save_fp
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	b	2f
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	ld	r5, VCPU_MSR(r9)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	.store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	.store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+2:
+#endif
+
 	/* Increment yield count if they have a VPA */
 	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
 	cmpdi	r8, 0

arch/powerpc/kvm/book3s_pr.c

@@ -1153,7 +1153,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 		goto free_vcpu;
 	vcpu->arch.book3s = vcpu_book3s;
 
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	vcpu->arch.shadow_vcpu =
 		kzalloc(sizeof(*vcpu->arch.shadow_vcpu), GFP_KERNEL);
 	if (!vcpu->arch.shadow_vcpu)
@@ -1198,7 +1198,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_shadow_vcpu:
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 free_vcpu3s:
 #endif
@@ -1215,7 +1215,7 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 
 	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
 	kvm_vcpu_uninit(vcpu);
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 #endif
 	vfree(vcpu_book3s);

arch/powerpc/mm/hash_utils_64.c

@@ -207,6 +207,10 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
+		/* Make kvm guest trampolines executable */
+		if (overlaps_kvm_tmp(vaddr, vaddr + step))
+			tprot &= ~HPTE_R_N;
+
 		/*
 		 * If relocatable, check if it overlaps interrupt vectors that
 		 * are copied down to real 0. For relocatable kernel