Merge branch 'fixes' into next

Merge our fixes branch to bring in some changes that are prerequisites
for work in next.

arch/powerpc/Kconfig

@@ -147,6 +147,7 @@ config PPC
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
+	select ARCH_SPLIT_ARG64			if PPC32
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC	if PPC_BOOK3S || PPC_8xx || 40x
@@ -285,7 +286,7 @@ config PPC
 	#
 
 config PPC_LONG_DOUBLE_128
-	depends on PPC64
+	depends on PPC64 && ALTIVEC
 	def_bool $(success,test "$(shell,echo __LONG_DOUBLE_128__ | $(CC) -E -P -)" = 1)
 
 config PPC_BARRIER_NOSPEC

arch/powerpc/include/asm/book3s/64/tlbflush-hash.h

@@ -32,6 +32,11 @@ static inline void arch_enter_lazy_mmu_mode(void)
 
 	if (radix_enabled())
 		return;
+	/*
+	 * apply_to_page_range can call us this preempt enabled when
+	 * operating on kernel page tables.
+	 */
+	preempt_disable();
 	batch = this_cpu_ptr(&ppc64_tlb_batch);
 	batch->active = 1;
 }
@@ -47,6 +52,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	if (batch->index)
 		__flush_tlb_pending(batch);
 	batch->active = 0;
+	preempt_enable();
 }
 
 #define arch_flush_lazy_mmu_mode()      do {} while (0)

arch/powerpc/include/asm/interrupt.h

@@ -602,6 +602,7 @@ ____##func(struct pt_regs *regs)
 /* kernel/traps.c */
 DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception);
 #ifdef CONFIG_PPC_BOOK3S_64
+DECLARE_INTERRUPT_HANDLER_RAW(machine_check_early_boot);
 DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async);
 #endif
 DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception);

arch/powerpc/include/asm/syscalls.h

@@ -104,6 +104,13 @@ long sys_ppc_ftruncate64(unsigned int fd, u32 reg4,
 			 unsigned long len1, unsigned long len2);
 long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2,
 			 size_t len, int advice);
+long sys_ppc_sync_file_range2(int fd, unsigned int flags,
+			      unsigned int offset1,
+			      unsigned int offset2,
+			      unsigned int nbytes1,
+			      unsigned int nbytes2);
+long sys_ppc_fallocate(int fd, int mode, u32 offset1, u32 offset2,
+		       u32 len1, u32 len2);
 #endif
 #ifdef CONFIG_COMPAT
 long compat_sys_mmap2(unsigned long addr, size_t len,

arch/powerpc/kernel/exceptions-64e.S

@@ -813,6 +813,13 @@ kernel_dbg_exc:
 	EXCEPTION_COMMON(0x260)
 	CHECK_NAPPING()
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+	/*
+	 * XXX: Returning from performance_monitor_exception taken as a
+	 * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return
+	 * and could cause bugs in return or elsewhere. That case should just
+	 * restore registers and return. There is a workaround for one known
+	 * problem in interrupt_exit_kernel_prepare().
+	 */
 	bl	performance_monitor_exception
 	b	interrupt_return
 

arch/powerpc/kernel/exceptions-64s.S

@@ -2357,9 +2357,21 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
 EXC_COMMON_BEGIN(performance_monitor_common)
 	GEN_COMMON performance_monitor
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	performance_monitor_exception
+	lbz	r4,PACAIRQSOFTMASK(r13)
+	cmpdi	r4,IRQS_ENABLED
+	bne	1f
+	bl	performance_monitor_exception_async
 	b	interrupt_return_srr
+1:
+	bl	performance_monitor_exception_nmi
+	/* Clear MSR_RI before setting SRR0 and SRR1. */
+	li	r9,0
+	mtmsrd	r9,1
 
+	kuap_kernel_restore r9, r10
+
+	EXCEPTION_RESTORE_REGS hsrr=0
+	RFI_TO_KERNEL
 
 /**
  * Interrupt 0xf20 - Vector Unavailable Interrupt.

arch/powerpc/kernel/interrupt.c

@@ -374,10 +374,18 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 	if (regs_is_unrecoverable(regs))
 		unrecoverable_exception(regs);
 	/*
-	 * CT_WARN_ON comes here via program_check_exception,
-	 * so avoid recursion.
+	 * CT_WARN_ON comes here via program_check_exception, so avoid
+	 * recursion.
+	 *
+	 * Skip the assertion on PMIs on 64e to work around a problem caused
+	 * by NMI PMIs incorrectly taking this interrupt return path, it's
+	 * possible for this to hit after interrupt exit to user switches
+	 * context to user. See also the comment in the performance monitor
+	 * handler in exceptions-64e.S
 	 */
-	if (TRAP(regs) != INTERRUPT_PROGRAM)
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
+	    TRAP(regs) != INTERRUPT_PROGRAM &&
+	    TRAP(regs) != INTERRUPT_PERFMON)
 		CT_WARN_ON(ct_state() == CONTEXT_USER);
 
 	kuap = kuap_get_and_assert_locked();

arch/powerpc/kernel/interrupt_64.S

@@ -532,15 +532,24 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
 	 * Returning to soft-disabled context.
 	 * Check if a MUST_HARD_MASK interrupt has become pending, in which
 	 * case we need to disable MSR[EE] in the return context.
+	 *
+	 * The MSR[EE] check catches among other things the short incoherency
+	 * in hard_irq_disable() between clearing MSR[EE] and setting
+	 * PACA_IRQ_HARD_DIS.
 	 */
 	ld	r12,_MSR(r1)
 	andi.	r10,r12,MSR_EE
 	beq	.Lfast_kernel_interrupt_return_\srr\() // EE already disabled
 	lbz	r11,PACAIRQHAPPENED(r13)
 	andi.	r10,r11,PACA_IRQ_MUST_HARD_MASK
-	beq	.Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending
+	bne	1f // HARD_MASK is pending
+	// No HARD_MASK pending, clear possible HARD_DIS set by interrupt
+	andi.	r11,r11,(~PACA_IRQ_HARD_DIS)@l
+	stb	r11,PACAIRQHAPPENED(r13)
+	b	.Lfast_kernel_interrupt_return_\srr\()
+
 
-	/* Must clear MSR_EE from _MSR */
+1:	/* Must clear MSR_EE from _MSR */
 #ifdef CONFIG_PPC_BOOK3S
 	li	r10,0
 	/* Clear valid before changing _MSR */

arch/powerpc/kernel/sys_ppc32.c

@@ -112,7 +112,7 @@ PPC32_SYSCALL_DEFINE6(ppc32_fadvise64,
 				 advice);
 }
 
-COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2,
+PPC32_SYSCALL_DEFINE6(ppc_sync_file_range2,
 		       int, fd, unsigned int, flags,
 		       unsigned int, offset1, unsigned int, offset2,
 		       unsigned int, nbytes1, unsigned int, nbytes2)
@@ -122,3 +122,14 @@ COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2,
 
 	return ksys_sync_file_range(fd, offset, nbytes, flags);
 }
+
+#ifdef CONFIG_PPC32
+SYSCALL_DEFINE6(ppc_fallocate,
+		int, fd, int, mode,
+		u32, offset1, u32, offset2, u32, len1, u32, len2)
+{
+	return ksys_fallocate(fd, mode,
+			      merge_64(offset1, offset2),
+			      merge_64(len1, len2));
+}
+#endif

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -394,8 +394,11 @@
 305	common	signalfd			sys_signalfd			compat_sys_signalfd
 306	common	timerfd_create			sys_timerfd_create
 307	common	eventfd				sys_eventfd
-308	common	sync_file_range2		sys_sync_file_range2		compat_sys_ppc_sync_file_range2
-309	nospu	fallocate			sys_fallocate			compat_sys_fallocate
+308	32	sync_file_range2		sys_ppc_sync_file_range2	compat_sys_ppc_sync_file_range2
+308	64	sync_file_range2		sys_sync_file_range2
+308	spu	sync_file_range2		sys_sync_file_range2
+309	32	fallocate			sys_ppc_fallocate		compat_sys_fallocate
+309	64	fallocate			sys_fallocate
 310	nospu	subpage_prot			sys_subpage_prot
 311	32	timerfd_settime			sys_timerfd_settime32
 311	64	timerfd_settime			sys_timerfd_settime

arch/powerpc/kernel/vmlinux.lds.S

@@ -142,7 +142,7 @@ SECTIONS
 #endif
 
 	.data.rel.ro : AT(ADDR(.data.rel.ro) - LOAD_OFFSET) {
-		*(.data.rel.ro*)
+		*(.data.rel.ro .data.rel.ro.*)
 	}
 
 	.branch_lt : AT(ADDR(.branch_lt) - LOAD_OFFSET) {

arch/powerpc/kvm/Kconfig

@@ -51,6 +51,7 @@ config KVM_BOOK3S_HV_POSSIBLE
 config KVM_BOOK3S_32
 	tristate "KVM support for PowerPC book3s_32 processors"
 	depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_BOOK3S_32_HANDLER
 	select KVM_BOOK3S_PR_POSSIBLE
@@ -105,6 +106,7 @@ config KVM_BOOK3S_64_HV
 config KVM_BOOK3S_64_PR
 	tristate "KVM support without using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
+	depends on !CONTEXT_TRACKING_USER
 	select KVM_BOOK3S_PR_POSSIBLE
 	help
 	  Support running guest kernels in virtual machines on processors
@@ -190,6 +192,7 @@ config KVM_EXIT_TIMING
 config KVM_E500V2
 	bool "KVM support for PowerPC E500v2 processors"
 	depends on PPC_E500 && !PPC_E500MC
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
 	select MMU_NOTIFIER
@@ -205,6 +208,7 @@ config KVM_E500V2
 config KVM_E500MC
 	bool "KVM support for PowerPC E500MC/E5500/E6500 processors"
 	depends on PPC_E500MC
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV

arch/powerpc/lib/vmx-helper.c

@@ -36,7 +36,17 @@ int exit_vmx_usercopy(void)
 {
 	disable_kernel_altivec();
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_no_resched();
+	/*
+	 * Must never explicitly call schedule (including preempt_enable())
+	 * while in a kuap-unlocked user copy, because the AMR register will
+	 * not be saved and restored across context switch. However preempt
+	 * kernels need to be preempted as soon as possible if need_resched is
+	 * set and we are preemptible. The hack here is to schedule a
+	 * decrementer to fire here and reschedule for us if necessary.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT) && need_resched())
+		set_dec(1);
 	return 0;
 }
 

arch/powerpc/mm/book3s64/hash_native.c

@@ -43,6 +43,29 @@
 
 static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map hpte_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("hpte_lock", &hpte_lock_map);
+
+static void acquire_hpte_lock(void)
+{
+	lock_map_acquire(&hpte_lock_map);
+}
+
+static void release_hpte_lock(void)
+{
+	lock_map_release(&hpte_lock_map);
+}
+#else
+static void acquire_hpte_lock(void)
+{
+}
+
+static void release_hpte_lock(void)
+{
+}
+#endif
+
 static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 						int apsize, int ssize)
 {
@@ -220,6 +243,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep)
 {
 	unsigned long *word = (unsigned long *)&hptep->v;
 
+	acquire_hpte_lock();
 	while (1) {
 		if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word))
 			break;
@@ -234,6 +258,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep)
 {
 	unsigned long *word = (unsigned long *)&hptep->v;
 
+	release_hpte_lock();
 	clear_bit_unlock(HPTE_LOCK_BIT, word);
 }
 
@@ -243,8 +268,11 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 {
 	struct hash_pte *hptep = htab_address + hpte_group;
 	unsigned long hpte_v, hpte_r;
+	unsigned long flags;
 	int i;
 
+	local_irq_save(flags);
+
 	if (!(vflags & HPTE_V_BOLTED)) {
 		DBG_LOW("    insert(group=%lx, vpn=%016lx, pa=%016lx,"
 			" rflags=%lx, vflags=%lx, psize=%d)\n",
@@ -263,8 +291,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 		hptep++;
 	}
 
-	if (i == HPTES_PER_GROUP)
+	if (i == HPTES_PER_GROUP) {
+		local_irq_restore(flags);
 		return -1;
+	}
 
 	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
 	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
@@ -286,10 +316,13 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	 * Now set the first dword including the valid bit
 	 * NOTE: this also unlocks the hpte
 	 */
+	release_hpte_lock();
 	hptep->v = cpu_to_be64(hpte_v);
 
 	__asm__ __volatile__ ("ptesync" : : : "memory");
 
+	local_irq_restore(flags);
+
 	return i | (!!(vflags & HPTE_V_SECONDARY) << 3);
 }
 
@@ -327,6 +360,7 @@ static long native_hpte_remove(unsigned long hpte_group)
 		return -1;
 
 	/* Invalidate the hpte. NOTE: this also unlocks it */
+	release_hpte_lock();
 	hptep->v = 0;
 
 	return i;
@@ -339,6 +373,9 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
 	int ret = 0, local = 0;
+	unsigned long irqflags;
+
+	local_irq_save(irqflags);
 
 	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 
@@ -382,6 +419,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	if (!(flags & HPTE_NOHPTE_UPDATE))
 		tlbie(vpn, bpsize, apsize, ssize, local);
 
+	local_irq_restore(irqflags);
+
 	return ret;
 }
 
@@ -445,6 +484,9 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	unsigned long vsid;
 	long slot;
 	struct hash_pte *hptep;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	vsid = get_kernel_vsid(ea, ssize);
 	vpn = hpt_vpn(ea, vsid, ssize);
@@ -463,6 +505,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	 * actual page size will be same.
 	 */
 	tlbie(vpn, psize, psize, ssize, 0);
+
+	local_irq_restore(flags);
 }
 
 /*
@@ -476,6 +520,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
 	unsigned long vsid;
 	long slot;
 	struct hash_pte *hptep;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	vsid = get_kernel_vsid(ea, ssize);
 	vpn = hpt_vpn(ea, vsid, ssize);
@@ -493,6 +540,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
 
 	/* Invalidate the TLB */
 	tlbie(vpn, psize, psize, ssize, 0);
+
+	local_irq_restore(flags);
+
 	return 0;
 }
 
@@ -517,10 +567,11 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 		/* recheck with locks held */
 		hpte_v = hpte_get_old_v(hptep);
 
-		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
+		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) {
 			/* Invalidate the hpte. NOTE: this also unlocks it */
+			release_hpte_lock();
 			hptep->v = 0;
-		else
+		} else
 			native_unlock_hpte(hptep);
 	}
 	/*
@@ -580,10 +631,8 @@ static void native_hugepage_invalidate(unsigned long vsid,
 			hpte_v = hpte_get_old_v(hptep);
 
 			if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) {
-				/*
-				 * Invalidate the hpte. NOTE: this also unlocks it
-				 */
-
+				/* Invalidate the hpte. NOTE: this also unlocks it */
+				release_hpte_lock();
 				hptep->v = 0;
 			} else
 				native_unlock_hpte(hptep);
@@ -765,8 +814,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 
 			if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
 				native_unlock_hpte(hptep);
-			else
+			else {
+				release_hpte_lock();
 				hptep->v = 0;
+			}
 
 		} pte_iterate_hashed_end();
 	}

arch/powerpc/mm/book3s64/hash_pgtable.c

@@ -404,7 +404,8 @@ EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage);
 
 struct change_memory_parms {
 	unsigned long start, end, newpp;
-	unsigned int step, nr_cpus, master_cpu;
+	unsigned int step, nr_cpus;
+	atomic_t master_cpu;
 	atomic_t cpu_counter;
 };
 
@@ -478,7 +479,8 @@ static int change_memory_range_fn(void *data)
 {
 	struct change_memory_parms *parms = data;
 
-	if (parms->master_cpu != smp_processor_id())
+	// First CPU goes through, all others wait.
+	if (atomic_xchg(&parms->master_cpu, 1) == 1)
 		return chmem_secondary_loop(parms);
 
 	// Wait for all but one CPU (this one) to call-in
@@ -516,7 +518,7 @@ static bool hash__change_memory_range(unsigned long start, unsigned long end,
 		chmem_parms.end = end;
 		chmem_parms.step = step;
 		chmem_parms.newpp = newpp;
-		chmem_parms.master_cpu = smp_processor_id();
+		atomic_set(&chmem_parms.master_cpu, 0);
 
 		cpus_read_lock();
 

arch/powerpc/mm/book3s64/hash_utils.c

@@ -1981,7 +1981,7 @@ long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
 }
 
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-static DEFINE_SPINLOCK(linear_map_hash_lock);
+static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
 
 static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 {
@@ -2005,10 +2005,10 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 				    mmu_linear_psize, mmu_kernel_ssize);
 
 	BUG_ON (ret < 0);
-	spin_lock(&linear_map_hash_lock);
+	raw_spin_lock(&linear_map_hash_lock);
 	BUG_ON(linear_map_hash_slots[lmi] & 0x80);
 	linear_map_hash_slots[lmi] = ret | 0x80;
-	spin_unlock(&linear_map_hash_lock);
+	raw_spin_unlock(&linear_map_hash_lock);
 }
 
 static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
@@ -2018,14 +2018,14 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
 
 	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
-	spin_lock(&linear_map_hash_lock);
+	raw_spin_lock(&linear_map_hash_lock);
 	if (!(linear_map_hash_slots[lmi] & 0x80)) {
-		spin_unlock(&linear_map_hash_lock);
+		raw_spin_unlock(&linear_map_hash_lock);
 		return;
 	}
 	hidx = linear_map_hash_slots[lmi] & 0x7f;
 	linear_map_hash_slots[lmi] = 0;
-	spin_unlock(&linear_map_hash_lock);
+	raw_spin_unlock(&linear_map_hash_lock);
 	if (hidx & _PTEIDX_SECONDARY)
 		hash = ~hash;
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;

arch/powerpc/net/bpf_jit_comp32.c

@@ -113,23 +113,19 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 {
 	int i;
 
-	/* First arg comes in as a 32 bits pointer. */
-	EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3));
-	EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
+	/* Initialize tail_call_cnt, to be skipped if we do tail calls. */
+	EMIT(PPC_RAW_LI(_R4, 0));
+
+#define BPF_TAILCALL_PROLOGUE_SIZE	4
+
 	EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
 
-	/*
-	 * Initialize tail_call_cnt in stack frame if we do tail calls.
-	 * Otherwise, put in NOPs so that it can be skipped when we are
-	 * invoked through a tail call.
-	 */
 	if (ctx->seen & SEEN_TAILCALL)
-		EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1,
-				 bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
-	else
-		EMIT(PPC_RAW_NOP());
+		EMIT(PPC_RAW_STW(_R4, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
 
-#define BPF_TAILCALL_PROLOGUE_SIZE	16
+	/* First arg comes in as a 32 bits pointer. */
+	EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3));
+	EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
 
 	/*
 	 * We need a stack frame, but we don't necessarily need to
@@ -170,24 +166,24 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 	for (i = BPF_PPC_NVR_MIN; i <= 31; i++)
 		if (bpf_is_seen_register(ctx, i))
 			EMIT(PPC_RAW_LWZ(i, _R1, bpf_jit_stack_offsetof(ctx, i)));
-}
-
-void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
-{
-	EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
-
-	bpf_jit_emit_common_epilogue(image, ctx);
-
-	/* Tear down our stack frame */
 
 	if (ctx->seen & SEEN_FUNC)
 		EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
 
+	/* Tear down our stack frame */
 	EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx)));
 
 	if (ctx->seen & SEEN_FUNC)
 		EMIT(PPC_RAW_MTLR(_R0));
 
+}
+
+void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
+{
+	EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
+
+	bpf_jit_emit_common_epilogue(image, ctx);
+
 	EMIT(PPC_RAW_BLR());
 }
 
@@ -244,7 +240,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29));
 	EMIT(PPC_RAW_ADD(_R3, _R3, b2p_bpf_array));
 	EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_array, ptrs)));
-	EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
 
 	/*
 	 * if (prog == NULL)
@@ -255,19 +250,14 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 
 	/* goto *(prog->bpf_func + prologue_size); */
 	EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_prog, bpf_func)));
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));
-
 	EMIT(PPC_RAW_ADDIC(_R3, _R3, BPF_TAILCALL_PROLOGUE_SIZE));
-
-	if (ctx->seen & SEEN_FUNC)
-		EMIT(PPC_RAW_MTLR(_R0));
-
 	EMIT(PPC_RAW_MTCTR(_R3));
 
 	EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_1)));
 
+	/* Put tail_call_cnt in r4 */
+	EMIT(PPC_RAW_MR(_R4, _R0));
+
 	/* tear restore NVRs, ... */
 	bpf_jit_emit_common_epilogue(image, ctx);
 

arch/powerpc/platforms/pseries/lparcfg.c

@@ -35,6 +35,7 @@
 #include <asm/drmem.h>
 
 #include "pseries.h"
+#include "vas.h"	/* pseries_vas_dlpar_cpu() */
 
 /*
  * This isn't a module but we expose that to userspace
@@ -748,6 +749,16 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf,
 			return -EINVAL;
 
 		retval = update_ppp(new_entitled_ptr, NULL);
+
+		if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
+			/*
+			 * The hypervisor assigns VAS resources based
+			 * on entitled capacity for shared mode.
+			 * Reconfig VAS windows based on DLPAR CPU events.
+			 */
+			if (pseries_vas_dlpar_cpu() != 0)
+				retval = H_HARDWARE;
+		}
 	} else if (!strcmp(kbuf, "capacity_weight")) {
 		char *endp;
 		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);

arch/powerpc/platforms/pseries/vas.c

@@ -200,16 +200,41 @@ static irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
 	struct vas_user_win_ref *tsk_ref;
 	int rc;
 
-	rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
-	if (!rc) {
-		tsk_ref = &txwin->vas_win.task_ref;
-		vas_dump_crb(&crb);
-		vas_update_csb(&crb, tsk_ref);
+	while (atomic_read(&txwin->pending_faults)) {
+		rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
+		if (!rc) {
+			tsk_ref = &txwin->vas_win.task_ref;
+			vas_dump_crb(&crb);
+			vas_update_csb(&crb, tsk_ref);
+		}
+		atomic_dec(&txwin->pending_faults);
 	}
 
 	return IRQ_HANDLED;
 }
 
+/*
+ * irq_default_primary_handler() can be used only with IRQF_ONESHOT
+ * which disables IRQ before executing the thread handler and enables
+ * it after. But this disabling interrupt sets the VAS IRQ OFF
+ * state in the hypervisor. If the NX generates fault interrupt
+ * during this window, the hypervisor will not deliver this
+ * interrupt to the LPAR. So use VAS specific IRQ handler instead
+ * of calling the default primary handler.
+ */
+static irqreturn_t pseries_vas_irq_handler(int irq, void *data)
+{
+	struct pseries_vas_window *txwin = data;
+
+	/*
+	 * The thread hanlder will process this interrupt if it is
+	 * already running.
+	 */
+	atomic_inc(&txwin->pending_faults);
+
+	return IRQ_WAKE_THREAD;
+}
+
 /*
  * Allocate window and setup IRQ mapping.
  */
@@ -240,8 +265,9 @@ static int allocate_setup_window(struct pseries_vas_window *txwin,
 		goto out_irq;
 	}
 
-	rc = request_threaded_irq(txwin->fault_virq, NULL,
-				  pseries_vas_fault_thread_fn, IRQF_ONESHOT,
+	rc = request_threaded_irq(txwin->fault_virq,
+				  pseries_vas_irq_handler,
+				  pseries_vas_fault_thread_fn, 0,
 				  txwin->name, txwin);
 	if (rc) {
 		pr_err("VAS-Window[%d]: Request IRQ(%u) failed with %d\n",
@@ -826,6 +852,25 @@ int vas_reconfig_capabilties(u8 type, int new_nr_creds)
 	mutex_unlock(&vas_pseries_mutex);
 	return rc;
 }
+
+int pseries_vas_dlpar_cpu(void)
+{
+	int new_nr_creds, rc;
+
+	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
+				      vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
+				      (u64)virt_to_phys(&hv_cop_caps));
+	if (!rc) {
+		new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
+		rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, new_nr_creds);
+	}
+
+	if (rc)
+		pr_err("Failed reconfig VAS capabilities with DLPAR\n");
+
+	return rc;
+}
+
 /*
  * Total number of default credits available (target_credits)
  * in LPAR depends on number of cores configured. It varies based on
@@ -840,7 +885,15 @@ static int pseries_vas_notifier(struct notifier_block *nb,
 	struct of_reconfig_data *rd = data;
 	struct device_node *dn = rd->dn;
 	const __be32 *intserv = NULL;
-	int new_nr_creds, len, rc = 0;
+	int len;
+
+	/*
+	 * For shared CPU partition, the hypervisor assigns total credits
+	 * based on entitled core capacity. So updating VAS windows will
+	 * be called from lparcfg_write().
+	 */
+	if (is_shared_processor())
+		return NOTIFY_OK;
 
 	if ((action == OF_RECONFIG_ATTACH_NODE) ||
 		(action == OF_RECONFIG_DETACH_NODE))
@@ -852,19 +905,7 @@ static int pseries_vas_notifier(struct notifier_block *nb,
 	if (!intserv)
 		return NOTIFY_OK;
 
-	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
-					vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
-					(u64)virt_to_phys(&hv_cop_caps));
-	if (!rc) {
-		new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
-		rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE,
-						new_nr_creds);
-	}
-
-	if (rc)
-		pr_err("Failed reconfig VAS capabilities with DLPAR\n");
-
-	return rc;
+	return pseries_vas_dlpar_cpu();
 }
 
 static struct notifier_block pseries_vas_nb = {

arch/powerpc/platforms/pseries/vas.h

@@ -132,6 +132,7 @@ struct pseries_vas_window {
 	u64 flags;
 	char *name;
 	int fault_virq;
+	atomic_t pending_faults; /* Number of pending faults */
 };
 
 int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps);
@@ -140,10 +141,15 @@ int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps);
 
 #ifdef CONFIG_PPC_VAS
 int vas_migration_handler(int action);
+int pseries_vas_dlpar_cpu(void);
 #else
 static inline int vas_migration_handler(int action)
 {
 	return 0;
 }
+static inline int pseries_vas_dlpar_cpu(void)
+{
+	return 0;
+}
 #endif
 #endif /* _VAS_H */

include/asm-generic/compat.h

@@ -15,7 +15,7 @@
 #endif
 
 #ifndef compat_arg_u64
-#ifdef CONFIG_CPU_BIG_ENDIAN
+#ifndef CONFIG_CPU_BIG_ENDIAN
 #define compat_arg_u64(name)		u32  name##_lo, u32  name##_hi
 #define compat_arg_u64_dual(name)	u32, name##_lo, u32, name##_hi
 #else