Merge branch 'fixes' into next

Merge our fixes branch, in particular to bring in the change to
arch/powerpc/boot/Makefile, which is depended upon by a subsequent
series.

arch/powerpc/Kconfig

@@ -906,11 +906,17 @@ config DATA_SHIFT
 
 config ARCH_FORCE_MAX_ORDER
 	int "Order of maximal physically contiguous allocations"
+	range 7 8 if PPC64 && PPC_64K_PAGES
 	default "8" if PPC64 && PPC_64K_PAGES
+	range 12 12 if PPC64 && !PPC_64K_PAGES
 	default "12" if PPC64 && !PPC_64K_PAGES
+	range 8 10 if PPC32 && PPC_16K_PAGES
 	default "8" if PPC32 && PPC_16K_PAGES
+	range 6 10 if PPC32 && PPC_64K_PAGES
 	default "6" if PPC32 && PPC_64K_PAGES
+	range 4 10 if PPC32 && PPC_256K_PAGES
 	default "4" if PPC32 && PPC_256K_PAGES
+	range 10 10
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically

arch/powerpc/boot/Makefile

@@ -34,8 +34,6 @@ endif
 
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		 -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \
-		 $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \
-		 $(call cc-option,-mno-mma) \
 		 $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \
 		 -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
 		 $(LINUXINCLUDE)
@@ -71,6 +69,10 @@ BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc
 
 BOOTARFLAGS	:= -crD
 
+BOOTCFLAGS	+= $(call cc-option,-mno-prefixed) \
+		   $(call cc-option,-mno-pcrel) \
+		   $(call cc-option,-mno-mma)
+
 ifdef CONFIG_CC_IS_CLANG
 BOOTCFLAGS += $(CLANG_FLAGS)
 BOOTAFLAGS += $(CLANG_FLAGS)

arch/powerpc/crypto/Kconfig

@@ -96,7 +96,7 @@ config CRYPTO_AES_PPC_SPE
 
 config CRYPTO_AES_GCM_P10
 	tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)"
-	depends on PPC64 && CPU_LITTLE_ENDIAN
+	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
 	select CRYPTO_LIB_AES
 	select CRYPTO_ALGAPI
 	select CRYPTO_AEAD

arch/powerpc/crypto/Makefile

@@ -22,15 +22,15 @@ sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
 sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
 crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
 crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
-aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp8-ppc.o aesp8-ppc.o
+aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@
 
-targets += aesp8-ppc.S ghashp8-ppc.S
+targets += aesp10-ppc.S ghashp10-ppc.S
 
-$(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
+$(obj)/aesp10-ppc.S $(obj)/ghashp10-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
 	$(call if_changed,perl)
 
-OBJECT_FILES_NON_STANDARD_aesp8-ppc.o := y
-OBJECT_FILES_NON_STANDARD_ghashp8-ppc.o := y
+OBJECT_FILES_NON_STANDARD_aesp10-ppc.o := y
+OBJECT_FILES_NON_STANDARD_ghashp10-ppc.o := y

arch/powerpc/crypto/aes-gcm-p10-glue.c

@@ -30,15 +30,15 @@ MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("aes");
 
-asmlinkage int aes_p8_set_encrypt_key(const u8 *userKey, const int bits,
+asmlinkage int aes_p10_set_encrypt_key(const u8 *userKey, const int bits,
 				      void *key);
-asmlinkage void aes_p8_encrypt(const u8 *in, u8 *out, const void *key);
+asmlinkage void aes_p10_encrypt(const u8 *in, u8 *out, const void *key);
 asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len,
 				    void *rkey, u8 *iv, void *Xi);
 asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len,
 				    void *rkey, u8 *iv, void *Xi);
 asmlinkage void gcm_init_htable(unsigned char htable[256], unsigned char Xi[16]);
-asmlinkage void gcm_ghash_p8(unsigned char *Xi, unsigned char *Htable,
+asmlinkage void gcm_ghash_p10(unsigned char *Xi, unsigned char *Htable,
 		unsigned char *aad, unsigned int alen);
 
 struct aes_key {
@@ -93,7 +93,7 @@ static void set_aad(struct gcm_ctx *gctx, struct Hash_ctx *hash,
 	gctx->aadLen = alen;
 	i = alen & ~0xf;
 	if (i) {
-		gcm_ghash_p8(nXi, hash->Htable+32, aad, i);
+		gcm_ghash_p10(nXi, hash->Htable+32, aad, i);
 		aad += i;
 		alen -= i;
 	}
@@ -102,7 +102,7 @@ static void set_aad(struct gcm_ctx *gctx, struct Hash_ctx *hash,
 			nXi[i] ^= aad[i];
 
 		memset(gctx->aad_hash, 0, 16);
-		gcm_ghash_p8(gctx->aad_hash, hash->Htable+32, nXi, 16);
+		gcm_ghash_p10(gctx->aad_hash, hash->Htable+32, nXi, 16);
 	} else {
 		memcpy(gctx->aad_hash, nXi, 16);
 	}
@@ -115,7 +115,7 @@ static void gcmp10_init(struct gcm_ctx *gctx, u8 *iv, unsigned char *rdkey,
 {
 	__be32 counter = cpu_to_be32(1);
 
-	aes_p8_encrypt(hash->H, hash->H, rdkey);
+	aes_p10_encrypt(hash->H, hash->H, rdkey);
 	set_subkey(hash->H);
 	gcm_init_htable(hash->Htable+32, hash->H);
 
@@ -126,7 +126,7 @@ static void gcmp10_init(struct gcm_ctx *gctx, u8 *iv, unsigned char *rdkey,
 	/*
 	 * Encrypt counter vector as iv tag and increment counter.
 	 */
-	aes_p8_encrypt(iv, gctx->ivtag, rdkey);
+	aes_p10_encrypt(iv, gctx->ivtag, rdkey);
 
 	counter = cpu_to_be32(2);
 	*((__be32 *)(iv+12)) = counter;
@@ -160,7 +160,7 @@ static void finish_tag(struct gcm_ctx *gctx, struct Hash_ctx *hash, int len)
 	/*
 	 * hash (AAD len and len)
 	 */
-	gcm_ghash_p8(hash->Htable, hash->Htable+32, aclen, 16);
+	gcm_ghash_p10(hash->Htable, hash->Htable+32, aclen, 16);
 
 	for (i = 0; i < 16; i++)
 		hash->Htable[i] ^= gctx->ivtag[i];
@@ -192,7 +192,7 @@ static int p10_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 	int ret;
 
 	vsx_begin();
-	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	ret = aes_p10_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
 	vsx_end();
 
 	return ret ? -EINVAL : 0;

arch/powerpc/crypto/aesp8-ppc.pl → arch/powerpc/crypto/aesp10-ppc.pl

@@ -110,7 +110,7 @@ die "can't locate ppc-xlate.pl";
 open STDOUT,"| $^X $xlate $flavour ".shift || die "can't call $xlate: $!";
 
 $FRAME=8*$SIZE_T;
-$prefix="aes_p8";
+$prefix="aes_p10";
 
 $sp="r1";
 $vrsave="r12";

arch/powerpc/crypto/ghashp8-ppc.pl → arch/powerpc/crypto/ghashp10-ppc.pl

@@ -64,7 +64,7 @@ $code=<<___;
 
 .text
 
-.globl	.gcm_init_p8
+.globl	.gcm_init_p10
 	lis		r0,0xfff0
 	li		r8,0x10
 	mfspr		$vrsave,256
@@ -110,7 +110,7 @@ $code=<<___;
 	.long		0
 	.byte		0,12,0x14,0,0,0,2,0
 	.long		0
-.size	.gcm_init_p8,.-.gcm_init_p8
+.size	.gcm_init_p10,.-.gcm_init_p10
 
 .globl	.gcm_init_htable
 	lis		r0,0xfff0
@@ -237,7 +237,7 @@ $code=<<___;
 	.long		0
 .size	.gcm_init_htable,.-.gcm_init_htable
 
-.globl	.gcm_gmult_p8
+.globl	.gcm_gmult_p10
 	lis		r0,0xfff8
 	li		r8,0x10
 	mfspr		$vrsave,256
@@ -283,9 +283,9 @@ $code=<<___;
 	.long		0
 	.byte		0,12,0x14,0,0,0,2,0
 	.long		0
-.size	.gcm_gmult_p8,.-.gcm_gmult_p8
+.size	.gcm_gmult_p10,.-.gcm_gmult_p10
 
-.globl	.gcm_ghash_p8
+.globl	.gcm_ghash_p10
 	lis		r0,0xfff8
 	li		r8,0x10
 	mfspr		$vrsave,256
@@ -350,7 +350,7 @@ Loop:
 	.long		0
 	.byte		0,12,0x14,0,0,0,4,0
 	.long		0
-.size	.gcm_ghash_p8,.-.gcm_ghash_p8
+.size	.gcm_ghash_p10,.-.gcm_ghash_p10
 
 .asciz  "GHASH for PowerISA 2.07, CRYPTOGAMS by <appro\@openssl.org>"
 .align  2

arch/powerpc/include/asm/iommu.h

@@ -205,7 +205,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group,
 				 int pci_domain_number, unsigned long pe_num);
 extern int iommu_add_device(struct iommu_table_group *table_group,
 		struct device *dev);
-extern void iommu_del_device(struct device *dev);
 extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction);
@@ -229,10 +228,6 @@ static inline int iommu_add_device(struct iommu_table_group *table_group,
 {
 	return 0;
 }
-
-static inline void iommu_del_device(struct device *dev)
-{
-}
 #endif /* !CONFIG_IOMMU_API */
 
 u64 dma_iommu_get_required_mask(struct device *dev);

arch/powerpc/kernel/dma-iommu.c

@@ -144,7 +144,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
 /* We support DMA to/from any memory page via the iommu */
 int dma_iommu_dma_supported(struct device *dev, u64 mask)
 {
-	struct iommu_table *tbl = get_iommu_table_base(dev);
+	struct iommu_table *tbl;
 
 	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
 		/*
@@ -162,6 +162,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 1;
 	}
 
+	tbl = get_iommu_table_base(dev);
+
 	if (!tbl) {
 		dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask);
 		return 0;

arch/powerpc/kernel/iommu.c

@@ -518,7 +518,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		/* Convert entry to a dma_addr_t */
 		entry += tbl->it_offset;
 		dma_addr = entry << tbl->it_page_shift;
-		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl));
+		dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl));
 
 		DBG("  - %lu pages, entry: %lx, dma_addr: %lx\n",
 			    npages, entry, dma_addr);
@@ -905,6 +905,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	unsigned int order;
 	unsigned int nio_pages, io_order;
 	struct page *page;
+	int tcesize = (1 << tbl->it_page_shift);
 
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
@@ -931,7 +932,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	nio_pages = size >> tbl->it_page_shift;
+	nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
+
 	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, 0);
@@ -939,7 +941,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 		free_pages((unsigned long)ret, order);
 		return NULL;
 	}
-	*dma_handle = mapping;
+
+	*dma_handle = mapping | ((u64)ret & (tcesize - 1));
 	return ret;
 }
 
@@ -950,7 +953,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 		unsigned int nio_pages;
 
 		size = PAGE_ALIGN(size);
-		nio_pages = size >> tbl->it_page_shift;
+		nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
 		iommu_free(tbl, dma_handle, nio_pages);
 		size = PAGE_ALIGN(size);
 		free_pages((unsigned long)vaddr, get_order(size));
@@ -1168,23 +1171,6 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_add_device);
 
-void iommu_del_device(struct device *dev)
-{
-	/*
-	 * Some devices might not have IOMMU table and group
-	 * and we needn't detach them from the associated
-	 * IOMMU groups
-	 */
-	if (!device_iommu_mapped(dev)) {
-		pr_debug("iommu_tce: skipping device %s with no tbl\n",
-			 dev_name(dev));
-		return;
-	}
-
-	iommu_group_remove_device(dev);
-}
-EXPORT_SYMBOL_GPL(iommu_del_device);
-
 /*
  * A simple iommu_table_group_ops which only allows reusing the existing
  * iommu_table. This handles VFIO for POWER7 or the nested KVM.

arch/powerpc/kernel/isa-bridge.c

@@ -93,11 +93,12 @@ static int process_ISA_OF_ranges(struct device_node *isa_node,
 	}
 
 inval_range:
-	if (!phb_io_base_phys) {
+	if (phb_io_base_phys) {
 		pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n");
 		remap_isa_base(phb_io_base_phys, 0x10000);
+		return 0;
 	}
-	return 0;
+	return -EINVAL;
 }
 
 

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -1040,8 +1040,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
 				  pte_t entry, unsigned long address, int psize)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED |
-					      _PAGE_RW | _PAGE_EXEC);
+	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY |
+					      _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
 
 	unsigned long change = pte_val(entry) ^ pte_val(*ptep);
 	/*

arch/powerpc/net/bpf_jit_comp.c

@@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		bpf_hdr = jit_data->header;
 		proglen = jit_data->proglen;
 		extra_pass = true;
+		/* During extra pass, ensure index is reset before repopulating extable entries */
+		cgctx.exentry_idx = 0;
 		goto skip_init_ctx;
 	}
 

arch/powerpc/platforms/Kconfig

@@ -265,6 +265,7 @@ config CPM2
 config FSL_ULI1575
 	bool "ULI1575 PCIe south bridge support"
 	depends on FSL_SOC_BOOKE || PPC_86xx
+	depends on PCI
 	select FSL_PCI
 	select GENERIC_ISA_DMA
 	help

arch/powerpc/platforms/powernv/pci.c

@@ -865,28 +865,3 @@ void __init pnv_pci_init(void)
 	/* Configure IOMMU DMA hooks */
 	set_pci_dma_ops(&dma_iommu_ops);
 }
-
-static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb,
-		unsigned long action, void *data)
-{
-	struct device *dev = data;
-
-	switch (action) {
-	case BUS_NOTIFY_DEL_DEVICE:
-		iommu_del_device(dev);
-		return 0;
-	default:
-		return 0;
-	}
-}
-
-static struct notifier_block pnv_tce_iommu_bus_nb = {
-	.notifier_call = pnv_tce_iommu_bus_notifier,
-};
-
-static int __init pnv_tce_iommu_bus_notifier_init(void)
-{
-	bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb);
-	return 0;
-}
-machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init);

arch/powerpc/platforms/pseries/iommu.c

@@ -91,19 +91,24 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		const char *node_name)
 {
-	struct iommu_table *tbl;
-
 	if (!table_group)
 		return;
 
-	tbl = table_group->tables[0];
 #ifdef CONFIG_IOMMU_API
 	if (table_group->group) {
 		iommu_group_put(table_group->group);
 		BUG_ON(table_group->group);
 	}
 #endif
-	iommu_tce_table_put(tbl);
+
+	/* Default DMA window table is at index 0, while DDW at 1. SR-IOV
+	 * adapters only have table on index 1.
+	 */
+	if (table_group->tables[0])
+		iommu_tce_table_put(table_group->tables[0]);
+
+	if (table_group->tables[1])
+		iommu_tce_table_put(table_group->tables[1]);
 
 	kfree(table_group);
 }
@@ -312,13 +317,22 @@ static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
 static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
 {
 	u64 rc;
+	long rpages = npages;
+	unsigned long limit;
 
 	if (!firmware_has_feature(FW_FEATURE_STUFF_TCE))
 		return tce_free_pSeriesLP(tbl->it_index, tcenum,
 					  tbl->it_page_shift, npages);
 
-	rc = plpar_tce_stuff((u64)tbl->it_index,
-			     (u64)tcenum << tbl->it_page_shift, 0, npages);
+	do {
+		limit = min_t(unsigned long, rpages, 512);
+
+		rc = plpar_tce_stuff((u64)tbl->it_index,
+				     (u64)tcenum << tbl->it_page_shift, 0, limit);
+
+		rpages -= limit;
+		tcenum += limit;
+	} while (rpages > 0 && !rc);
 
 	if (rc && printk_ratelimit()) {
 		printk("tce_freemulti_pSeriesLP: plpar_tce_stuff failed\n");
@@ -1695,31 +1709,6 @@ static int __init disable_multitce(char *str)
 
 __setup("multitce=", disable_multitce);
 
-static int tce_iommu_bus_notifier(struct notifier_block *nb,
-		unsigned long action, void *data)
-{
-	struct device *dev = data;
-
-	switch (action) {
-	case BUS_NOTIFY_DEL_DEVICE:
-		iommu_del_device(dev);
-		return 0;
-	default:
-		return 0;
-	}
-}
-
-static struct notifier_block tce_iommu_bus_nb = {
-	.notifier_call = tce_iommu_bus_notifier,
-};
-
-static int __init tce_iommu_bus_notifier_init(void)
-{
-	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
-	return 0;
-}
-machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init);
-
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose,
 					     struct pci_dev *pdev)

arch/powerpc/xmon/xmon.c

@@ -88,7 +88,7 @@ static unsigned long ndump = 64;
 static unsigned long nidump = 16;
 static unsigned long ncsum = 4096;
 static int termch;
-static char tmpstr[128];
+static char tmpstr[KSYM_NAME_LEN];
 static int tracing_enabled;
 
 static long bus_error_jmp[JMP_BUF_LEN];