Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "Here is the bulk of the powerpc changes for this merge window.  It got
  a bit delayed in part because I wasn't paying attention, and in part
  because I discovered I had a core PCI change without a PCI maintainer
  ack in it.  Bjorn eventually agreed it was ok to merge it though we'll
  probably improve it later and I didn't want to rebase to add his ack.

  There is going to be a bit more next week, essentially fixes that I
  still want to sort through and test.

  The biggest item this time is the support to build the ppc64 LE kernel
  with our new v2 ABI.  We previously supported v2 userspace but the
  kernel itself was a tougher nut to crack.  This is now sorted mostly
  thanks to Anton and Rusty.

  We also have a fairly big series from Cedric that add support for
  64-bit LE zImage boot wrapper.  This was made harder by the fact that
  traditionally our zImage wrapper was always 32-bit, but our new LE
  toolchains don't really support 32-bit anymore (it's somewhat there
  but not really "supported") so we didn't want to rely on it.  This
  meant more churn that just endian fixes.

  This brings some more LE bits as well, such as the ability to run in
  LE mode without a hypervisor (ie. under OPAL firmware) by doing the
  right OPAL call to reinitialize the CPU to take HV interrupts in the
  right mode and the usual pile of endian fixes.

  There's another series from Gavin adding EEH improvements (one day we
  *will* have a release with less than 20 EEH patches, I promise!).

  Another highlight is the support for the "Split core" functionality on
  P8 by Michael.  This allows a P8 core to be split into "sub cores" of
  4 threads which allows the subcores to run different guests under KVM
  (the HW still doesn't support a partition per thread).

  And then the usual misc bits and fixes ..."

[ Further delayed by gmail deciding that BenH is a dirty spammer.
  Google knows.  ]

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (155 commits)
  powerpc/powernv: Add missing include to LPC code
  selftests/powerpc: Test the THP bug we fixed in the previous commit
  powerpc/mm: Check paca psize is up to date for huge mappings
  powerpc/powernv: Pass buffer size to OPAL validate flash call
  powerpc/pseries: hcall functions are exported to modules, need _GLOBAL_TOC()
  powerpc: Exported functions __clear_user and copy_page use r2 so need _GLOBAL_TOC()
  powerpc/powernv: Set memory_block_size_bytes to 256MB
  powerpc: Allow ppc_md platform hook to override memory_block_size_bytes
  powerpc/powernv: Fix endian issues in memory error handling code
  powerpc/eeh: Skip eeh sysfs when eeh is disabled
  powerpc: 64bit sendfile is capped at 2GB
  powerpc/powernv: Provide debugfs access to the LPC bus via OPAL
  powerpc/serial: Use saner flags when creating legacy ports
  powerpc: Add cpu family documentation
  powerpc/xmon: Fix up xmon format strings
  powerpc/powernv: Add calls to support little endian host
  powerpc: Document sysfs DSCR interface
  powerpc: Fix regression of per-CPU DSCR setting
  powerpc: Split __SYSFS_SPRSETUP macro
  arch: powerpc/fadump: Cleaning up inconsistent NULL checks
  ...

5 files changed, 71 insertions, 35 deletions

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index aba05bbb3e74..7a12edbb61e7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1236,7 +1236,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	int core;
 	struct kvmppc_vcore *vcore;
 
-	core = id / threads_per_core;
+	core = id / threads_per_subcore;
 	if (core >= KVM_MAX_VCORES)
 		goto out;
 
@@ -1286,7 +1286,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 			init_waitqueue_head(&vcore->wq);
 			vcore->preempt_tb = TB_NIL;
 			vcore->lpcr = kvm->arch.lpcr;
-			vcore->first_vcpuid = core * threads_per_core;
+			vcore->first_vcpuid = core * threads_per_subcore;
 			vcore->kvm = kvm;
 		}
 		kvm->arch.vcores[core] = vcore;
@@ -1476,16 +1476,19 @@ static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
 static int on_primary_thread(void)
 {
 	int cpu = smp_processor_id();
-	int thr = cpu_thread_in_core(cpu);
+	int thr;
 
-	if (thr)
+	/* Are we on a primary subcore? */
+	if (cpu_thread_in_subcore(cpu))
 		return 0;
-	while (++thr < threads_per_core)
+
+	thr = 0;
+	while (++thr < threads_per_subcore)
 		if (cpu_online(cpu + thr))
 			return 0;
 
 	/* Grab all hw threads so they can't go into the kernel */
-	for (thr = 1; thr < threads_per_core; ++thr) {
+	for (thr = 1; thr < threads_per_subcore; ++thr) {
 		if (kvmppc_grab_hwthread(cpu + thr)) {
 			/* Couldn't grab one; let the others go */
 			do {
@@ -1544,15 +1547,18 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	}
 
 	/*
-	 * Make sure we are running on thread 0, and that
-	 * secondary threads are offline.
+	 * Make sure we are running on primary threads, and that secondary
+	 * threads are offline.  Also check if the number of threads in this
+	 * guest are greater than the current system threads per guest.
 	 */
-	if (threads_per_core > 1 && !on_primary_thread()) {
+	if ((threads_per_core > 1) &&
+	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
 		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
 			vcpu->arch.ret = -EBUSY;
 		goto out;
 	}
 
+
 	vc->pcpu = smp_processor_id();
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		kvmppc_start_thread(vcpu);
@@ -1580,7 +1586,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	/* wait for secondary threads to finish writing their state to memory */
 	if (vc->nap_count < vc->n_woken)
 		kvmppc_wait_for_nap(vc);
-	for (i = 0; i < threads_per_core; ++i)
+	for (i = 0; i < threads_per_subcore; ++i)
 		kvmppc_release_hwthread(vc->pcpu + i);
 	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
 	vc->vcore_state = VCORE_EXITING;
@@ -2305,10 +2311,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	spin_lock_init(&kvm->arch.slot_phys_lock);
 
 	/*
-	 * Don't allow secondary CPU threads to come online
-	 * while any KVM VMs exist.
+	 * Track that we now have a HV mode VM active. This blocks secondary
+	 * CPU threads from coming online.
 	 */
-	inhibit_secondary_onlining();
+	kvm_hv_vm_activated();
 
 	return 0;
 }
@@ -2324,7 +2330,7 @@ static void kvmppc_free_vcores(struct kvm *kvm)
 
 static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 {
-	uninhibit_secondary_onlining();
+	kvm_hv_vm_deactivated();
 
 	kvmppc_free_vcores(kvm);
 	if (kvm->arch.rma) {
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8cd0daebb82d..7cde8a665205 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/cpu.h>
 #include <linux/kvm_host.h>
 #include <linux/preempt.h>
 #include <linux/export.h>
@@ -181,3 +182,33 @@ void __init kvm_cma_reserve(void)
 		kvm_cma_declare_contiguous(selected_size, align_size);
 	}
 }
+
+/*
+ * When running HV mode KVM we need to block certain operations while KVM VMs
+ * exist in the system. We use a counter of VMs to track this.
+ *
+ * One of the operations we need to block is onlining of secondaries, so we
+ * protect hv_vm_count with get/put_online_cpus().
+ */
+static atomic_t hv_vm_count;
+
+void kvm_hv_vm_activated(void)
+{
+	get_online_cpus();
+	atomic_inc(&hv_vm_count);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(kvm_hv_vm_activated);
+
+void kvm_hv_vm_deactivated(void)
+{
+	get_online_cpus();
+	atomic_dec(&hv_vm_count);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(kvm_hv_vm_deactivated);
+
+bool kvm_hv_mode_active(void)
+{
+	return atomic_read(&hv_vm_count) != 0;
+}
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index e18e3cfc32de..8c86422a1e37 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -171,7 +171,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 #endif /* CONFIG_SMP */
 
 	/* Jump to partition switch code */
-	bl	.kvmppc_hv_entry_trampoline
+	bl	kvmppc_hv_entry_trampoline
 	nop
 
 /*
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 974793435a2e..77356fd25ccc 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -292,8 +292,7 @@ kvm_start_guest:
 	beq	kvm_no_guest
 
 	/* Set HSTATE_DSCR(r13) to something sensible */
-	LOAD_REG_ADDR(r6, dscr_default)
-	ld	r6, 0(r6)
+	ld	r6, PACA_DSCR(r13)
 	std	r6, HSTATE_DSCR(r13)
 
 	bl	kvmppc_hv_entry
@@ -1799,7 +1798,7 @@ kvmppc_hdsi:
 	/* Search the hash table. */
 	mr	r3, r9			/* vcpu pointer */
 	li	r7, 1			/* data fault */
-	bl	.kvmppc_hpte_hv_fault
+	bl	kvmppc_hpte_hv_fault
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	ld	r10, VCPU_PC(r9)
 	ld	r11, VCPU_MSR(r9)
@@ -1873,7 +1872,7 @@ kvmppc_hisi:
 	mr	r4, r10
 	mr	r6, r11
 	li	r7, 0			/* instruction fault */
-	bl	.kvmppc_hpte_hv_fault
+	bl	kvmppc_hpte_hv_fault
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	ld	r10, VCPU_PC(r9)
 	ld	r11, VCPU_MSR(r9)
@@ -1947,16 +1946,16 @@ hcall_real_fallback:
 	.globl	hcall_real_table
 hcall_real_table:
 	.long	0		/* 0 - unused */
-	.long	.kvmppc_h_remove - hcall_real_table
-	.long	.kvmppc_h_enter - hcall_real_table
-	.long	.kvmppc_h_read - hcall_real_table
+	.long	DOTSYM(kvmppc_h_remove) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_enter) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_read) - hcall_real_table
 	.long	0		/* 0x10 - H_CLEAR_MOD */
 	.long	0		/* 0x14 - H_CLEAR_REF */
-	.long	.kvmppc_h_protect - hcall_real_table
-	.long	.kvmppc_h_get_tce - hcall_real_table
-	.long	.kvmppc_h_put_tce - hcall_real_table
+	.long	DOTSYM(kvmppc_h_protect) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_get_tce) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_put_tce) - hcall_real_table
 	.long	0		/* 0x24 - H_SET_SPRG0 */
-	.long	.kvmppc_h_set_dabr - hcall_real_table
+	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
 	.long	0		/* 0x2c */
 	.long	0		/* 0x30 */
 	.long	0		/* 0x34 */
@@ -1972,11 +1971,11 @@ hcall_real_table:
 	.long	0		/* 0x5c */
 	.long	0		/* 0x60 */
 #ifdef CONFIG_KVM_XICS
-	.long	.kvmppc_rm_h_eoi - hcall_real_table
-	.long	.kvmppc_rm_h_cppr - hcall_real_table
-	.long	.kvmppc_rm_h_ipi - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table
 	.long	0		/* 0x70 - H_IPOLL */
-	.long	.kvmppc_rm_h_xirr - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table
 #else
 	.long	0		/* 0x64 - H_EOI */
 	.long	0		/* 0x68 - H_CPPR */
@@ -2010,7 +2009,7 @@ hcall_real_table:
 	.long	0		/* 0xd4 */
 	.long	0		/* 0xd8 */
 	.long	0		/* 0xdc */
-	.long	.kvmppc_h_cede - hcall_real_table
+	.long	DOTSYM(kvmppc_h_cede) - hcall_real_table
 	.long	0		/* 0xe4 */
 	.long	0		/* 0xe8 */
 	.long	0		/* 0xec */
@@ -2027,11 +2026,11 @@ hcall_real_table:
 	.long	0		/* 0x118 */
 	.long	0		/* 0x11c */
 	.long	0		/* 0x120 */
-	.long	.kvmppc_h_bulk_remove - hcall_real_table
+	.long	DOTSYM(kvmppc_h_bulk_remove) - hcall_real_table
 	.long	0		/* 0x128 */
 	.long	0		/* 0x12c */
 	.long	0		/* 0x130 */
-	.long	.kvmppc_h_set_xdabr - hcall_real_table
+	.long	DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
 hcall_real_table_end:
 
 ignore_hdec:
@@ -2256,7 +2255,7 @@ kvm_cede_exit:
 	/* Try to handle a machine check in real mode */
 machine_check_realmode:
 	mr	r3, r9		/* get vcpu pointer */
-	bl	.kvmppc_realmode_machine_check
+	bl	kvmppc_realmode_machine_check
 	nop
 	cmpdi	r3, 0		/* continue exiting from guest? */
 	ld	r9, HSTATE_KVM_VCPU(r13)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index bab20f410443..61c738ab1283 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -426,7 +426,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_SMT:
 		if (hv_enabled)
-			r = threads_per_core;
+			r = threads_per_subcore;
 		else
 			r = 0;
 		break;