Merge tag 'powerpc-4.10-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "Two fixes for fallout from the hugetlb changes we merged this cycle.

  Ten other fixes, four only affect Power9, and the rest are a bit of a
  mixture though nothing terrible.

  Thanks to: Aneesh Kumar K.V, Anton Blanchard, Benjamin Herrenschmidt,
  Dave Martin, Gavin Shan, Madhavan Srinivasan, Nicholas Piggin, Reza
  Arbab"

* tag 'powerpc-4.10-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc: Ignore reserved field in DCSR and PVR reads and writes
  powerpc/ptrace: Preserve previous TM fprs/vsrs on short regset write
  powerpc/ptrace: Preserve previous fprs/vsrs on short regset write
  powerpc/perf: Use MSR to report privilege level on P9 DD1
  selftest/powerpc: Wrong PMC initialized in pmc56_overflow test
  powerpc/eeh: Enable IO path on permanent error
  powerpc/perf: Fix PM_BRU_CMPL event code for power9
  powerpc/mm: Fix little-endian 4K hugetlb
  powerpc/mm/hugetlb: Don't panic when we don't find the default huge page size
  powerpc: Fix pgtable pmd cache init
  powerpc/icp-opal: Fix missing KVM case and harden replay
  powerpc/mm: Fix memory hotplug BUG() on radix

arch/powerpc/include/asm/book3s/64/hash-4k.h

@@ -36,12 +36,13 @@
 #ifdef CONFIG_HUGETLB_PAGE
 static inline int hash__hugepd_ok(hugepd_t hpd)
 {
+	unsigned long hpdval = hpd_val(hpd);
 	/*
 	 * if it is not a pte and have hugepd shift mask
 	 * set, then it is a hugepd directory pointer
 	 */
-	if (!(hpd.pd & _PAGE_PTE) &&
-	    ((hpd.pd & HUGEPD_SHIFT_MASK) != 0))
+	if (!(hpdval & _PAGE_PTE) &&
+	    ((hpdval & HUGEPD_SHIFT_MASK) != 0))
 		return true;
 	return false;
 }

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

@@ -201,6 +201,10 @@ extern int __meminit hash__vmemmap_create_mapping(unsigned long start,
 					      unsigned long phys);
 extern void hash__vmemmap_remove_mapping(unsigned long start,
 				     unsigned long page_size);
+
+int hash__create_section_mapping(unsigned long start, unsigned long end);
+int hash__remove_section_mapping(unsigned long start, unsigned long end);
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */

arch/powerpc/include/asm/hugetlb.h

@@ -21,12 +21,12 @@ static inline pte_t *hugepd_page(hugepd_t hpd)
 	 * We have only four bits to encode, MMU page size
 	 */
 	BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
-	return __va(hpd.pd & HUGEPD_ADDR_MASK);
+	return __va(hpd_val(hpd) & HUGEPD_ADDR_MASK);
 }
 
 static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
 {
-	return (hpd.pd & HUGEPD_SHIFT_MASK) >> 2;
+	return (hpd_val(hpd) & HUGEPD_SHIFT_MASK) >> 2;
 }
 
 static inline unsigned int hugepd_shift(hugepd_t hpd)
@@ -52,18 +52,20 @@ static inline pte_t *hugepd_page(hugepd_t hpd)
 {
 	BUG_ON(!hugepd_ok(hpd));
 #ifdef CONFIG_PPC_8xx
-	return (pte_t *)__va(hpd.pd & ~(_PMD_PAGE_MASK | _PMD_PRESENT_MASK));
+	return (pte_t *)__va(hpd_val(hpd) &
+			     ~(_PMD_PAGE_MASK | _PMD_PRESENT_MASK));
 #else
-	return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
+	return (pte_t *)((hpd_val(hpd) &
+			  ~HUGEPD_SHIFT_MASK) | PD_HUGE);
 #endif
 }
 
 static inline unsigned int hugepd_shift(hugepd_t hpd)
 {
 #ifdef CONFIG_PPC_8xx
-	return ((hpd.pd & _PMD_PAGE_MASK) >> 1) + 17;
+	return ((hpd_val(hpd) & _PMD_PAGE_MASK) >> 1) + 17;
 #else
-	return hpd.pd & HUGEPD_SHIFT_MASK;
+	return hpd_val(hpd) & HUGEPD_SHIFT_MASK;
 #endif
 }
 

arch/powerpc/include/asm/nohash/pgtable.h

@@ -227,9 +227,10 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 static inline int hugepd_ok(hugepd_t hpd)
 {
 #ifdef CONFIG_PPC_8xx
-	return ((hpd.pd & 0x4) != 0);
+	return ((hpd_val(hpd) & 0x4) != 0);
 #else
-	return (hpd.pd > 0);
+	/* We clear the top bit to indicate hugepd */
+	return ((hpd_val(hpd) & PD_HUGE) ==  0);
 #endif
 }
 

arch/powerpc/include/asm/page.h

@@ -294,15 +294,12 @@ extern long long virt_phys_offset;
 #include <asm/pgtable-types.h>
 #endif
 
-typedef struct { signed long pd; } hugepd_t;
 
 #ifndef CONFIG_HUGETLB_PAGE
 #define is_hugepd(pdep)		(0)
 #define pgd_huge(pgd)		(0)
 #endif /* CONFIG_HUGETLB_PAGE */
 
-#define __hugepd(x) ((hugepd_t) { (x) })
-
 struct page;
 extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
 extern void copy_user_page(void *to, void *from, unsigned long vaddr,

arch/powerpc/include/asm/perf_event_server.h

@@ -65,6 +65,7 @@ struct power_pmu {
 #define PPMU_HAS_SSLOT		0x00000020 /* Has sampled slot in MMCRA */
 #define PPMU_HAS_SIER		0x00000040 /* Has SIER */
 #define PPMU_ARCH_207S		0x00000080 /* PMC is architecture v2.07S */
+#define PPMU_NO_SIAR		0x00000100 /* Do not use SIAR */
 
 /*
  * Values for flags to get_alternatives()

arch/powerpc/include/asm/pgtable-be-types.h

@@ -104,4 +104,12 @@ static inline bool pmd_xchg(pmd_t *pmdp, pmd_t old, pmd_t new)
 	return pmd_raw(old) == prev;
 }
 
+typedef struct { __be64 pdbe; } hugepd_t;
+#define __hugepd(x) ((hugepd_t) { cpu_to_be64(x) })
+
+static inline unsigned long hpd_val(hugepd_t x)
+{
+	return be64_to_cpu(x.pdbe);
+}
+
 #endif /* _ASM_POWERPC_PGTABLE_BE_TYPES_H */

arch/powerpc/include/asm/pgtable-types.h

@@ -66,4 +66,11 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new)
 }
 #endif
 
+typedef struct { unsigned long pd; } hugepd_t;
+#define __hugepd(x) ((hugepd_t) { (x) })
+static inline unsigned long hpd_val(hugepd_t x)
+{
+	return x.pd;
+}
+
 #endif /* _ASM_POWERPC_PGTABLE_TYPES_H */

arch/powerpc/include/asm/ppc-opcode.h

@@ -157,7 +157,7 @@
 #define PPC_INST_MCRXR			0x7c000400
 #define PPC_INST_MCRXR_MASK		0xfc0007fe
 #define PPC_INST_MFSPR_PVR		0x7c1f42a6
-#define PPC_INST_MFSPR_PVR_MASK		0xfc1fffff
+#define PPC_INST_MFSPR_PVR_MASK		0xfc1ffffe
 #define PPC_INST_MFTMR			0x7c0002dc
 #define PPC_INST_MSGSND			0x7c00019c
 #define PPC_INST_MSGCLR			0x7c0001dc
@@ -174,13 +174,13 @@
 #define PPC_INST_RFDI			0x4c00004e
 #define PPC_INST_RFMCI			0x4c00004c
 #define PPC_INST_MFSPR_DSCR		0x7c1102a6
-#define PPC_INST_MFSPR_DSCR_MASK	0xfc1fffff
+#define PPC_INST_MFSPR_DSCR_MASK	0xfc1ffffe
 #define PPC_INST_MTSPR_DSCR		0x7c1103a6
-#define PPC_INST_MTSPR_DSCR_MASK	0xfc1fffff
+#define PPC_INST_MTSPR_DSCR_MASK	0xfc1ffffe
 #define PPC_INST_MFSPR_DSCR_USER	0x7c0302a6
-#define PPC_INST_MFSPR_DSCR_USER_MASK	0xfc1fffff
+#define PPC_INST_MFSPR_DSCR_USER_MASK	0xfc1ffffe
 #define PPC_INST_MTSPR_DSCR_USER	0x7c0303a6
-#define PPC_INST_MTSPR_DSCR_USER_MASK	0xfc1fffff
+#define PPC_INST_MTSPR_DSCR_USER_MASK	0xfc1ffffe
 #define PPC_INST_MFVSRD			0x7c000066
 #define PPC_INST_MTVSRD			0x7c000166
 #define PPC_INST_SLBFEE			0x7c0007a7

arch/powerpc/kernel/eeh.c

@@ -298,9 +298,17 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 	 *
 	 * For pHyp, we have to enable IO for log retrieval. Otherwise,
 	 * 0xFF's is always returned from PCI config space.
+	 *
+	 * When the @severity is EEH_LOG_PERM, the PE is going to be
+	 * removed. Prior to that, the drivers for devices included in
+	 * the PE will be closed. The drivers rely on working IO path
+	 * to bring the devices to quiet state. Otherwise, PCI traffic
+	 * from those devices after they are removed is like to cause
+	 * another unexpected EEH error.
 	 */
 	if (!(pe->type & EEH_PE_PHB)) {
-		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
+		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+		    severity == EEH_LOG_PERM)
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
 		/*

arch/powerpc/kernel/ptrace.c

@@ -463,6 +463,10 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 
 	flush_fp_to_thread(target);
 
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.TS_FPR(i);
+	buf[32] = target->thread.fp_state.fpscr;
+
 	/* copy to local buffer then write that out */
 	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
 	if (i)
@@ -672,6 +676,9 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset,
 	flush_altivec_to_thread(target);
 	flush_vsx_to_thread(target);
 
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 buf, 0, 32 * sizeof(double));
 	if (!ret)
@@ -1019,6 +1026,10 @@ static int tm_cfpr_set(struct task_struct *target,
 	flush_fp_to_thread(target);
 	flush_altivec_to_thread(target);
 
+	for (i = 0; i < 32; i++)
+		buf[i] = target->thread.TS_CKFPR(i);
+	buf[32] = target->thread.ckfp_state.fpscr;
+
 	/* copy to local buffer then write that out */
 	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
 	if (i)
@@ -1283,6 +1294,9 @@ static int tm_cvsx_set(struct task_struct *target,
 	flush_altivec_to_thread(target);
 	flush_vsx_to_thread(target);
 
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 buf, 0, 32 * sizeof(double));
 	if (!ret)

arch/powerpc/mm/hash_utils_64.c

@@ -747,7 +747,7 @@ static unsigned long __init htab_get_table_size(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int create_section_mapping(unsigned long start, unsigned long end)
+int hash__create_section_mapping(unsigned long start, unsigned long end)
 {
 	int rc = htab_bolt_mapping(start, end, __pa(start),
 				   pgprot_val(PAGE_KERNEL), mmu_linear_psize,
@@ -761,7 +761,7 @@ int create_section_mapping(unsigned long start, unsigned long end)
 	return rc;
 }
 
-int remove_section_mapping(unsigned long start, unsigned long end)
+int hash__remove_section_mapping(unsigned long start, unsigned long end)
 {
 	int rc = htab_remove_mapping(start, end, mmu_linear_psize,
 				     mmu_kernel_ssize);

arch/powerpc/mm/hugetlbpage-hash64.c

@@ -125,11 +125,14 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 int hugepd_ok(hugepd_t hpd)
 {
 	bool is_hugepd;
+	unsigned long hpdval;
+
+	hpdval = hpd_val(hpd);
 
 	/*
 	 * We should not find this format in page directory, warn otherwise.
 	 */
-	is_hugepd = (((hpd.pd & 0x3) == 0x0) && ((hpd.pd & HUGEPD_SHIFT_MASK) != 0));
+	is_hugepd = (((hpdval & 0x3) == 0x0) && ((hpdval & HUGEPD_SHIFT_MASK) != 0));
 	WARN(is_hugepd, "Found wrong page directory format\n");
 	return 0;
 }

arch/powerpc/mm/hugetlbpage.c

@@ -53,7 +53,7 @@ static u64 gpage_freearray[MAX_NUMBER_GPAGES];
 static unsigned nr_gpages;
 #endif
 
-#define hugepd_none(hpd)	((hpd).pd == 0)
+#define hugepd_none(hpd)	(hpd_val(hpd) == 0)
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
@@ -103,24 +103,24 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	for (i = 0; i < num_hugepd; i++, hpdp++) {
 		if (unlikely(!hugepd_none(*hpdp)))
 			break;
-		else
+		else {
 #ifdef CONFIG_PPC_BOOK3S_64
-			hpdp->pd = __pa(new) |
-				   (shift_to_mmu_psize(pshift) << 2);
+			*hpdp = __hugepd(__pa(new) |
+					 (shift_to_mmu_psize(pshift) << 2));
 #elif defined(CONFIG_PPC_8xx)
-			hpdp->pd = __pa(new) |
-				   (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M :
-							      _PMD_PAGE_512K) |
-				   _PMD_PRESENT;
+			*hpdp = __hugepd(__pa(new) |
+					 (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M :
+					  _PMD_PAGE_512K) | _PMD_PRESENT);
 #else
 			/* We use the old format for PPC_FSL_BOOK3E */
-			hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+			*hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift);
 #endif
+		}
 	}
 	/* If we bailed from the for loop early, an error occurred, clean up */
 	if (i < num_hugepd) {
 		for (i = i - 1 ; i >= 0; i--, hpdp--)
-			hpdp->pd = 0;
+			*hpdp = __hugepd(0);
 		kmem_cache_free(cachep, new);
 	}
 	spin_unlock(&mm->page_table_lock);
@@ -454,7 +454,7 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 		return;
 
 	for (i = 0; i < num_hugepd; i++, hpdp++)
-		hpdp->pd = 0;
+		*hpdp = __hugepd(0);
 
 	if (shift >= pdshift)
 		hugepd_free(tlb, hugepte);
@@ -810,12 +810,8 @@ static int __init hugetlbpage_init(void)
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.
 		 */
-		if (pdshift > shift) {
+		if (pdshift > shift)
 			pgtable_cache_add(pdshift - shift, NULL);
-			if (!PGT_CACHE(pdshift - shift))
-				panic("hugetlbpage_init(): could not create "
-				      "pgtable cache for %d bit pagesize\n", shift);
-		}
 #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 		else if (!hugepte_cache) {
 			/*
@@ -852,9 +848,6 @@ static int __init hugetlbpage_init(void)
 	else if (mmu_psize_defs[MMU_PAGE_2M].shift)
 		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_2M].shift;
 #endif
-	else
-		panic("%s: Unable to set default huge page size\n", __func__);
-
 	return 0;
 }
 

arch/powerpc/mm/init-common.c

@@ -78,8 +78,12 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
 	align = max_t(unsigned long, align, minalign);
 	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
 	new = kmem_cache_create(name, table_size, align, 0, ctor);
+	if (!new)
+		panic("Could not allocate pgtable cache for order %d", shift);
+
 	kfree(name);
 	pgtable_cache[shift - 1] = new;
+
 	pr_debug("Allocated pgtable cache for order %d\n", shift);
 }
 
@@ -88,7 +92,7 @@ void pgtable_cache_init(void)
 {
 	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
 
-	if (PMD_INDEX_SIZE && !PGT_CACHE(PMD_INDEX_SIZE))
+	if (PMD_CACHE_INDEX && !PGT_CACHE(PMD_CACHE_INDEX))
 		pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
 	/*
 	 * In all current configs, when the PUD index exists it's the
@@ -97,11 +101,4 @@ void pgtable_cache_init(void)
 	 */
 	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
 		pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);
-
-	if (!PGT_CACHE(PGD_INDEX_SIZE))
-		panic("Couldn't allocate pgd cache");
-	if (PMD_INDEX_SIZE && !PGT_CACHE(PMD_INDEX_SIZE))
-		panic("Couldn't allocate pmd pgtable caches");
-	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
-		panic("Couldn't allocate pud pgtable caches");
 }

arch/powerpc/mm/pgtable-book3s64.c

@@ -126,3 +126,21 @@ void mmu_cleanup_all(void)
 	else if (mmu_hash_ops.hpte_clear_all)
 		mmu_hash_ops.hpte_clear_all();
 }
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int create_section_mapping(unsigned long start, unsigned long end)
+{
+	if (radix_enabled())
+		return -ENODEV;
+
+	return hash__create_section_mapping(start, end);
+}
+
+int remove_section_mapping(unsigned long start, unsigned long end)
+{
+	if (radix_enabled())
+		return -ENODEV;
+
+	return hash__remove_section_mapping(start, end);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */

arch/powerpc/perf/core-book3s.c

@@ -295,6 +295,8 @@ static inline void perf_read_regs(struct pt_regs *regs)
 	 */
 	if (TRAP(regs) != 0xf00)
 		use_siar = 0;
+	else if ((ppmu->flags & PPMU_NO_SIAR))
+		use_siar = 0;
 	else if (marked)
 		use_siar = 1;
 	else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))

arch/powerpc/perf/power9-events-list.h

@@ -16,7 +16,7 @@ EVENT(PM_CYC,					0x0001e)
 EVENT(PM_ICT_NOSLOT_CYC,			0x100f8)
 EVENT(PM_CMPLU_STALL,				0x1e054)
 EVENT(PM_INST_CMPL,				0x00002)
-EVENT(PM_BRU_CMPL,				0x40060)
+EVENT(PM_BRU_CMPL,				0x10012)
 EVENT(PM_BR_MPRED_CMPL,				0x400f6)
 
 /* All L1 D cache load references counted at finish, gated by reject */

arch/powerpc/perf/power9-pmu.c

@@ -384,7 +384,7 @@ static struct power_pmu power9_isa207_pmu = {
 	.bhrb_filter_map	= power9_bhrb_filter_map,
 	.get_constraint		= isa207_get_constraint,
 	.disable_pmc		= isa207_disable_pmc,
-	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S,
+	.flags			= PPMU_NO_SIAR | PPMU_ARCH_207S,
 	.n_generic		= ARRAY_SIZE(power9_generic_events),
 	.generic_events		= power9_generic_events,
 	.cache_events		= &power9_cache_events,

arch/powerpc/sysdev/xics/icp-opal.c

@@ -20,6 +20,7 @@
 #include <asm/xics.h>
 #include <asm/io.h>
 #include <asm/opal.h>
+#include <asm/kvm_ppc.h>
 
 static void icp_opal_teardown_cpu(void)
 {
@@ -39,7 +40,26 @@ static void icp_opal_flush_ipi(void)
 	 * Should we be flagging idle loop instead?
 	 * Or creating some task to be scheduled?
 	 */
-	opal_int_eoi((0x00 << 24) | XICS_IPI);
+	if (opal_int_eoi((0x00 << 24) | XICS_IPI) > 0)
+		force_external_irq_replay();
+}
+
+static unsigned int icp_opal_get_xirr(void)
+{
+	unsigned int kvm_xirr;
+	__be32 hw_xirr;
+	int64_t rc;
+
+	/* Handle an interrupt latched by KVM first */
+	kvm_xirr = kvmppc_get_xics_latch();
+	if (kvm_xirr)
+		return kvm_xirr;
+
+	/* Then ask OPAL */
+	rc = opal_int_get_xirr(&hw_xirr, false);
+	if (rc < 0)
+		return 0;
+	return be32_to_cpu(hw_xirr);
 }
 
 static unsigned int icp_opal_get_irq(void)
@@ -47,12 +67,8 @@ static unsigned int icp_opal_get_irq(void)
 	unsigned int xirr;
 	unsigned int vec;
 	unsigned int irq;
-	int64_t rc;
 
-	rc = opal_int_get_xirr(&xirr, false);
-	if (rc < 0)
-		return 0;
-	xirr = be32_to_cpu(xirr);
+	xirr = icp_opal_get_xirr();
 	vec = xirr & 0x00ffffff;
 	if (vec == XICS_IRQ_SPURIOUS)
 		return 0;
@@ -67,7 +83,8 @@ static unsigned int icp_opal_get_irq(void)
 	xics_mask_unknown_vec(vec);
 
 	/* We might learn about it later, so EOI it */
-	opal_int_eoi(xirr);
+	if (opal_int_eoi(xirr) > 0)
+		force_external_irq_replay();
 
 	return 0;
 }