Linux 5.12-rc3

-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmBOgu4eHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGUd0H/3Ey8aWjVAig9Pe+
 VQVZKwG+LXWH6UmUx5qyaTxophhmGnWLvkigJMn63qIg4eQtfp2gNFHK+T4OJNIP
 ybnkjFZ337x4J9zD6m8mt4Wmelq9iW2wNOS+3YZAyYiGlXfMGM7SlYRCQRQznTED
 2O/JCMsOoP+Z8tr5ah/bzs0dANsXmTZ3QqRP2uzb6irKTgFR3/weOhj+Ht1oJ4Aq
 V+bgdcwhtk20hJhlvVeqws+o74LR789tTDCknlz/YNMv9e6VPfyIQ5vJAcFmZATE
 Ezj9yzkZ4IU+Ux6ikAyaFyBU8d1a4Wqye3eHCZBsEo6tcSAhbTZ90eoU86vh6ajS
 LZjwkNw=
 =6y1u
 -----END PGP SIGNATURE-----

Merge tag 'v5.12-rc3' into x86/cleanups, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.yaml

@@ -23,6 +23,7 @@ properties:
           - enum:
               - ingenic,jz4775-intc
               - ingenic,jz4770-intc
+              - ingenic,jz4760b-intc
           - const: ingenic,jz4760-intc
       - items:
           - const: ingenic,x1000-intc

Documentation/gpu/todo.rst

@@ -613,6 +613,27 @@ Some of these date from the very introduction of KMS in 2008 ...
 
 Level: Intermediate
 
+Remove automatic page mapping from dma-buf importing
+----------------------------------------------------
+
+When importing dma-bufs, the dma-buf and PRIME frameworks automatically map
+imported pages into the importer's DMA area. drm_gem_prime_fd_to_handle() and
+drm_gem_prime_handle_to_fd() require that importers call dma_buf_attach()
+even if they never do actual device DMA, but only CPU access through
+dma_buf_vmap(). This is a problem for USB devices, which do not support DMA
+operations.
+
+To fix the issue, automatic page mappings should be removed from the
+buffer-sharing code. Fixing this is a bit more involved, since the import/export
+cache is also tied to &drm_gem_object.import_attach. Meanwhile we paper over
+this problem for USB devices by fishing out the USB host controller device, as
+long as that supports DMA. Otherwise importing can still needlessly fail.
+
+Contact: Thomas Zimmermann <tzimmermann@suse.de>, Daniel Vetter
+
+Level: Advanced
+
+
 Better Testing
 ==============
 

Documentation/networking/bonding.rst

@@ -1988,7 +1988,7 @@ netif_carrier.
 If use_carrier is 0, then the MII monitor will first query the
 device's (via ioctl) MII registers and check the link state.  If that
 request fails (not just that it returns carrier down), then the MII
-monitor will make an ethtool ETHOOL_GLINK request to attempt to obtain
+monitor will make an ethtool ETHTOOL_GLINK request to attempt to obtain
 the same information.  If both methods fail (i.e., the driver either
 does not support or had some error in processing both the MII register
 and ethtool requests), then the MII monitor will assume the link is

Documentation/networking/netdev-FAQ.rst

@@ -142,73 +142,13 @@ Please send incremental versions on top of what has been merged in order to fix
 the patches the way they would look like if your latest patch series was to be
 merged.
 
-How can I tell what patches are queued up for backporting to the various stable releases?
+Are there special rules regarding stable submissions on netdev?
------------------------------------------------------------------------------------------
-Normally Greg Kroah-Hartman collects stable commits himself, but for
-networking, Dave collects up patches he deems critical for the
-networking subsystem, and then hands them off to Greg.
-
-There is a patchworks queue that you can see here:
-
-  https://patchwork.kernel.org/bundle/netdev/stable/?state=*
-
-It contains the patches which Dave has selected, but not yet handed off
-to Greg.  If Greg already has the patch, then it will be here:
-
-  https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git
-
-A quick way to find whether the patch is in this stable-queue is to
-simply clone the repo, and then git grep the mainline commit ID, e.g.
-::
-
-  stable-queue$ git grep -l 284041ef21fdf2e
-  releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-  releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-  releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-  stable/stable-queue$
-
-I see a network patch and I think it should be backported to stable. Should I request it via stable@vger.kernel.org like the references in the kernel's Documentation/process/stable-kernel-rules.rst file say?
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
-No, not for networking.  Check the stable queues as per above first
-to see if it is already queued.  If not, then send a mail to netdev,
-listing the upstream commit ID and why you think it should be a stable
-candidate.
-
-Before you jump to go do the above, do note that the normal stable rules
-in :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
-still apply.  So you need to explicitly indicate why it is a critical
-fix and exactly what users are impacted.  In addition, you need to
-convince yourself that you *really* think it has been overlooked,
-vs. having been considered and rejected.
-
-Generally speaking, the longer it has had a chance to "soak" in
-mainline, the better the odds that it is an OK candidate for stable.  So
-scrambling to request a commit be added the day after it appears should
-be avoided.
-
-I have created a network patch and I think it should be backported to stable. Should I add a Cc: stable@vger.kernel.org like the references in the kernel's Documentation/ directory say?
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
-No.  See above answer.  In short, if you think it really belongs in
-stable, then ensure you write a decent commit log that describes who
-gets impacted by the bug fix and how it manifests itself, and when the
-bug was introduced.  If you do that properly, then the commit will get
-handled appropriately and most likely get put in the patchworks stable
-queue if it really warrants it.
-
-If you think there is some valid information relating to it being in
-stable that does *not* belong in the commit log, then use the three dash
-marker line as described in
-:ref:`Documentation/process/submitting-patches.rst <the_canonical_patch_format>`
-to temporarily embed that information into the patch that you send.
-
-Are all networking bug fixes backported to all stable releases?
 ---------------------------------------------------------------
-Due to capacity, Dave could only take care of the backports for the
+While it used to be the case that netdev submissions were not supposed
-last two stable releases. For earlier stable releases, each stable
+to carry explicit ``CC: stable@vger.kernel.org`` tags that is no longer
-branch maintainer is supposed to take care of them. If you find any
+the case today. Please follow the standard stable rules in
-patch is missing from an earlier stable branch, please notify
+:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`,
-stable@vger.kernel.org with either a commit ID or a formal patch
+and make sure you include appropriate Fixes tags!
-backported, and CC Dave and other relevant networking developers.
 
 Is the comment style convention different for the networking content?
 ---------------------------------------------------------------------

Documentation/process/stable-kernel-rules.rst

@@ -35,12 +35,6 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 Procedure for submitting patches to the -stable tree
 ----------------------------------------------------
 
- - If the patch covers files in net/ or drivers/net please follow netdev stable
-   submission guidelines as described in
-   :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>`
-   after first checking the stable networking queue at
-   https://patchwork.kernel.org/bundle/netdev/stable/?state=*
-   to ensure the requested patch is not already queued up.
  - Security patches should not be handled (solely) by the -stable review
    process but should follow the procedures in
    :ref:`Documentation/admin-guide/security-bugs.rst <securitybugs>`.

Documentation/process/submitting-patches.rst

@@ -250,11 +250,6 @@ should also read
 :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
 in addition to this file.
 
-Note, however, that some subsystem maintainers want to come to their own
-conclusions on which patches should go to the stable trees.  The networking
-maintainer, in particular, would rather not see individual developers
-adding lines like the above to their patches.
-
 If changes affect userland-kernel interfaces, please send the MAN-PAGES
 maintainer (as listed in the MAINTAINERS file) a man-pages patch, or at
 least a notification of the change, so that some information makes its way

Documentation/virt/kvm/api.rst

@@ -182,6 +182,9 @@ is dependent on the CPU capability and the kernel configuration. The limit can
 be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
 ioctl() at run-time.
 
+Creation of the VM will fail if the requested IPA size (whether it is
+implicit or explicit) is unsupported on the host.
+
 Please note that configuring the IPA size does not affect the capability
 exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
 size of the address translated by the stage2 level (guest physical to

MAINTAINERS

@@ -261,8 +261,8 @@ ABI/API
 L:	linux-api@vger.kernel.org
 F:	include/linux/syscalls.h
 F:	kernel/sys_ni.c
-F:	include/uapi/
+X:	include/uapi/
-F:	arch/*/include/uapi/
+X:	arch/*/include/uapi/
 
 ABIT UGURU 1,2 HARDWARE MONITOR DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
@@ -5835,7 +5835,7 @@ M:	David Airlie <airlied@linux.ie>
 M:	Daniel Vetter <daniel@ffwll.ch>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
-B:	https://bugs.freedesktop.org/
+B:	https://gitlab.freedesktop.org/drm
 C:	irc://chat.freenode.net/dri-devel
 T:	git git://anongit.freedesktop.org/drm/drm
 F:	Documentation/devicetree/bindings/display/
@@ -10716,7 +10716,8 @@ F:	drivers/net/ethernet/marvell/mvpp2/
 
 MARVELL MWIFIEX WIRELESS DRIVER
 M:	Amitkumar Karwar <amitkarwar@gmail.com>
-M:	Ganapathi Bhat <ganapathi.bhat@nxp.com>
+M:	Ganapathi Bhat <ganapathi017@gmail.com>
+M:	Sharvari Harisangam <sharvari.harisangam@nxp.com>
 M:	Xinming Hu <huxinming820@gmail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
@@ -19165,7 +19166,7 @@ S:	Maintained
 F:	drivers/infiniband/hw/vmw_pvrdma/
 
 VMware PVSCSI driver
-M:	Jim Gill <jgill@vmware.com>
+M:	Vishal Bhakta <vbhakta@vmware.com>
 M:	VMware PV-Drivers <pv-drivers@vmware.com>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Frozen Wasteland
 
 # *DOCUMENTATION*
@@ -264,7 +264,8 @@ no-dot-config-targets := $(clean-targets) \
 			 $(version_h) headers headers_% archheaders archscripts \
 			 %asm-generic kernelversion %src-pkg dt_binding_check \
 			 outputmakefile
-no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease
+no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \
+			  image_name
 single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
 
 config-build	:=
@@ -478,6 +479,7 @@ USERINCLUDE    := \
 		-I$(objtree)/arch/$(SRCARCH)/include/generated/uapi \
 		-I$(srctree)/include/uapi \
 		-I$(objtree)/include/generated/uapi \
+                -include $(srctree)/include/linux/compiler-version.h \
                 -include $(srctree)/include/linux/kconfig.h
 
 # Use LINUXINCLUDE when you must reference the include/ directory.

arch/Kconfig

@@ -632,13 +632,12 @@ config HAS_LTO_CLANG
 	def_bool y
 	# Clang >= 11: https://github.com/ClangBuiltLinux/linux/issues/510
 	depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD
-	depends on $(success,test $(LLVM) -eq 1)
 	depends on $(success,test $(LLVM_IAS) -eq 1)
 	depends on $(success,$(NM) --help | head -n 1 | grep -qi llvm)
 	depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm)
 	depends on ARCH_SUPPORTS_LTO_CLANG
 	depends on !FTRACE_MCOUNT_USE_RECORDMCOUNT
-	depends on !KASAN
+	depends on !KASAN || KASAN_HW_TAGS
 	depends on !GCOV_KERNEL
 	help
 	  The compiler and Kconfig options support building with Clang's

arch/arm/Kconfig

@@ -348,6 +348,7 @@ config ARCH_EP93XX
 	select ARM_AMBA
 	imply ARM_PATCH_PHYS_VIRT
 	select ARM_VIC
+	select GENERIC_IRQ_MULTI_HANDLER
 	select AUTO_ZRELADDR
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO

arch/arm/xen/p2m.c

@@ -11,6 +11,7 @@
 
 #include <xen/xen.h>
 #include <xen/interface/memory.h>
+#include <xen/grant_table.h>
 #include <xen/page.h>
 #include <xen/swiotlb-xen.h>
 
@@ -109,7 +110,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 		map_ops[i].status = GNTST_general_error;
 		unmap.host_addr = map_ops[i].host_addr,
 		unmap.handle = map_ops[i].handle;
-		map_ops[i].handle = ~0;
+		map_ops[i].handle = INVALID_GRANT_HANDLE;
 		if (map_ops[i].flags & GNTMAP_device_map)
 			unmap.dev_bus_addr = map_ops[i].dev_bus_addr;
 		else
@@ -130,7 +131,6 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
 
 int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 			      struct gnttab_unmap_grant_ref *kunmap_ops,
@@ -145,7 +145,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
 
 bool __set_phys_to_machine_multi(unsigned long pfn,
 		unsigned long mfn, unsigned long nr_pages)

arch/arm64/Kconfig

@@ -1055,8 +1055,6 @@ config HW_PERF_EVENTS
 config SYS_SUPPORTS_HUGETLBFS
 	def_bool y
 
-config ARCH_WANT_HUGE_PMD_SHARE
-
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
@@ -1157,8 +1155,8 @@ config XEN
 
 config FORCE_MAX_ZONEORDER
 	int
-	default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
+	default "14" if ARM64_64K_PAGES
-	default "12" if (ARM64_16K_PAGES && TRANSPARENT_HUGEPAGE)
+	default "12" if ARM64_16K_PAGES
 	default "11"
 	help
 	  The kernel memory allocator divides physically contiguous memory
@@ -1855,12 +1853,6 @@ config CMDLINE_FROM_BOOTLOADER
 	  the boot loader doesn't provide any, the default kernel command
 	  string provided in CMDLINE will be used.
 
-config CMDLINE_EXTEND
-	bool "Extend bootloader kernel arguments"
-	help
-	  The command-line arguments provided by the boot loader will be
-	  appended to the default kernel command string.
-
 config CMDLINE_FORCE
 	bool "Always use the default kernel command string"
 	help

arch/arm64/include/asm/kvm_asm.h

@@ -47,10 +47,10 @@
 #define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context		2
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa		3
 #define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid		4
-#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_local_vmid	5
+#define __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context		5
 #define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff		6
 #define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs			7
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_ich_vtr_el2		8
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config		8
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr		9
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr		10
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs		11
@@ -183,16 +183,16 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
 
 extern void __kvm_flush_vm_context(void);
+extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 				     int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
-extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_get_gic_config(void);
 extern u64 __vgic_v3_read_vmcr(void);
 extern void __vgic_v3_write_vmcr(u32 vmcr);
 extern void __vgic_v3_init_lrs(void);

arch/arm64/include/asm/kvm_hyp.h

@@ -83,6 +83,11 @@ void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
 void __debug_switch_to_host(struct kvm_vcpu *vcpu);
 
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+#endif
+
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
 
@@ -97,7 +102,8 @@ bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt);
 
 void __noreturn hyp_panic(void);
 #ifdef __KVM_NVHE_HYPERVISOR__
-void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+			       u64 elr, u64 par);
 #endif
 
 #endif /* __ARM64_KVM_HYP_H__ */

arch/arm64/include/asm/memory.h

@@ -328,6 +328,11 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
 #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
+#define page_to_virt(x)	({						\
+	__typeof__(x) __page = x;					\
+	void *__addr = __va(page_to_phys(__page));			\
+	(void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
+})
 #define virt_to_page(x)		pfn_to_page(virt_to_pfn(x))
 #else
 #define page_to_virt(x)	({						\

arch/arm64/include/asm/mmu_context.h

@@ -63,23 +63,6 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
 extern u64 idmap_t0sz;
 extern u64 idmap_ptrs_per_pgd;
 
-static inline bool __cpu_uses_extended_idmap(void)
-{
-	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52))
-		return false;
-
-	return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS));
-}
-
-/*
- * True if the extended ID map requires an extra level of translation table
- * to be configured.
- */
-static inline bool __cpu_uses_extended_idmap_level(void)
-{
-	return ARM64_HW_PGTABLE_LEVELS(64 - idmap_t0sz) > CONFIG_PGTABLE_LEVELS;
-}
-
 /*
  * Ensure TCR.T0SZ is set to the provided value.
  */

arch/arm64/include/asm/pgtable-prot.h

@@ -66,7 +66,6 @@ extern bool arm64_use_ng_mappings;
 #define _PAGE_DEFAULT		(_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
 
 #define PAGE_KERNEL		__pgprot(PROT_NORMAL)
-#define PAGE_KERNEL_TAGGED	__pgprot(PROT_NORMAL_TAGGED)
 #define PAGE_KERNEL_RO		__pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
 #define PAGE_KERNEL_ROX		__pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(PROT_NORMAL & ~PTE_PXN)

arch/arm64/include/asm/pgtable.h

@@ -486,6 +486,9 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
 #define pgprot_device(prot) \
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN)
+#define pgprot_tagged(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED))
+#define pgprot_mhp	pgprot_tagged
 /*
  * DMA allocations for non-coherent devices use what the Arm architecture calls
  * "Normal non-cacheable" memory, which permits speculation, unaligned accesses

arch/arm64/include/asm/sysreg.h

@@ -796,6 +796,11 @@
 #define ID_AA64MMFR0_PARANGE_48		0x5
 #define ID_AA64MMFR0_PARANGE_52		0x6
 
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT	0x0
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE	0x1
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN	0x2
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX	0x7
+
 #ifdef CONFIG_ARM64_PA_BITS_52
 #define ID_AA64MMFR0_PARANGE_MAX	ID_AA64MMFR0_PARANGE_52
 #else
@@ -961,14 +966,17 @@
 #define ID_PFR1_PROGMOD_SHIFT		0
 
 #if defined(CONFIG_ARM64_4K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN4_SHIFT
+#define ID_AA64MMFR0_TGRAN_SHIFT		ID_AA64MMFR0_TGRAN4_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN4_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_TGRAN4_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX	0x7
 #elif defined(CONFIG_ARM64_16K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN16_SHIFT
+#define ID_AA64MMFR0_TGRAN_SHIFT		ID_AA64MMFR0_TGRAN16_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN16_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_TGRAN16_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX	0xF
 #elif defined(CONFIG_ARM64_64K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN64_SHIFT
+#define ID_AA64MMFR0_TGRAN_SHIFT		ID_AA64MMFR0_TGRAN64_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN64_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_TGRAN64_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX	0x7
 #endif
 
 #define MVFR2_FPMISC_SHIFT		4

arch/arm64/kernel/head.S

@@ -319,7 +319,7 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 	 */
 	adrp	x5, __idmap_text_end
 	clz	x5, x5
-	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
+	cmp	x5, TCR_T0SZ(VA_BITS_MIN) // default T0SZ small enough?
 	b.ge	1f			// .. then skip VA range extension
 
 	adr_l	x6, idmap_t0sz
@@ -655,8 +655,10 @@ SYM_FUNC_END(__secondary_too_slow)
 SYM_FUNC_START(__enable_mmu)
 	mrs	x2, ID_AA64MMFR0_EL1
 	ubfx	x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
-	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
+	cmp     x2, #ID_AA64MMFR0_TGRAN_SUPPORTED_MIN
-	b.ne	__no_granule_support
+	b.lt    __no_granule_support
+	cmp     x2, #ID_AA64MMFR0_TGRAN_SUPPORTED_MAX
+	b.gt    __no_granule_support
 	update_early_cpu_boot_status 0, x2, x3
 	adrp	x2, idmap_pg_dir
 	phys_to_ttbr x1, x1

arch/arm64/kernel/idreg-override.c

@@ -163,33 +163,36 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases)
 	} while (1);
 }
 
+static __init const u8 *get_bootargs_cmdline(void)
+{
+	const u8 *prop;
+	void *fdt;
+	int node;
+
+	fdt = get_early_fdt_ptr();
+	if (!fdt)
+		return NULL;
+
+	node = fdt_path_offset(fdt, "/chosen");
+	if (node < 0)
+		return NULL;
+
+	prop = fdt_getprop(fdt, node, "bootargs", NULL);
+	if (!prop)
+		return NULL;
+
+	return strlen(prop) ? prop : NULL;
+}
+
 static __init void parse_cmdline(void)
 {
-	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) {
+	const u8 *prop = get_bootargs_cmdline();
-		const u8 *prop;
-		void *fdt;
-		int node;
 
-		fdt = get_early_fdt_ptr();
+	if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop)
-		if (!fdt)
+		__parse_cmdline(CONFIG_CMDLINE, true);
-			goto out;
-
-		node = fdt_path_offset(fdt, "/chosen");
-		if (node < 0)
-			goto out;
-
-		prop = fdt_getprop(fdt, node, "bootargs", NULL);
-		if (!prop)
-			goto out;
 
+	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop)
 		__parse_cmdline(prop, true);
-
-		if (!IS_ENABLED(CONFIG_CMDLINE_EXTEND))
-			return;
-	}
-
-out:
-	__parse_cmdline(CONFIG_CMDLINE, true);
 }
 
 /* Keep checkers quiet */

arch/arm64/kernel/image-vars.h

@@ -101,6 +101,9 @@ KVM_NVHE_ALIAS(__stop___kvm_ex_table);
 /* Array containing bases of nVHE per-CPU memory regions. */
 KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base);
 
+/* PMU available static key */
+KVM_NVHE_ALIAS(kvm_arm_pmu_available);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */

arch/arm64/kernel/perf_event.c

@@ -460,7 +460,7 @@ static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
 	return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
 }
 
-static inline u32 armv8pmu_read_evcntr(int idx)
+static inline u64 armv8pmu_read_evcntr(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
 

arch/arm64/kvm/arm.c

@@ -385,11 +385,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
+	 * We guarantee that both TLBs and I-cache are private to each
+	 * vcpu. If detecting that a vcpu from the same VM has
+	 * previously run on the same physical CPU, call into the
+	 * hypervisor code to nuke the relevant contexts.
+	 *
 	 * We might get preempted before the vCPU actually runs, but
 	 * over-invalidation doesn't affect correctness.
 	 */
 	if (*last_ran != vcpu->vcpu_id) {
-		kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
+		kvm_call_hyp(__kvm_flush_cpu_context, mmu);
 		*last_ran = vcpu->vcpu_id;
 	}
 

arch/arm64/kvm/hyp/entry.S

@@ -85,8 +85,10 @@ SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 
 	// If the hyp context is loaded, go straight to hyp_panic
 	get_loaded_vcpu x0, x1
-	cbz	x0, hyp_panic
+	cbnz	x0, 1f
+	b	hyp_panic
 
+1:
 	// The hyp context is saved so make sure it is restored to allow
 	// hyp_panic to run at hyp and, subsequently, panic to run in the host.
 	// This makes use of __guest_exit to avoid duplication but sets the
@@ -94,7 +96,7 @@ SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 	// current state is saved to the guest context but it will only be
 	// accurate if the guest had been completely restored.
 	adr_this_cpu x0, kvm_hyp_ctxt, x1
-	adr	x1, hyp_panic
+	adr_l	x1, hyp_panic
 	str	x1, [x0, #CPU_XREG_OFFSET(30)]
 
 	get_vcpu_ptr	x1, x0
@@ -146,7 +148,7 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// Now restore the hyp regs
 	restore_callee_saved_regs x2
 
-	set_loaded_vcpu xzr, x1, x2
+	set_loaded_vcpu xzr, x2, x3
 
 alternative_if ARM64_HAS_RAS_EXTN
 	// If we have the RAS extensions we can consume a pending error

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -90,15 +90,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
 	 * EL1 instead of being trapped to EL2.
 	 */
-	write_sysreg(0, pmselr_el0);
+	if (kvm_arm_support_pmu_v3()) {
-	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+		write_sysreg(0, pmselr_el0);
+		write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	}
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 }
 
 static inline void __deactivate_traps_common(void)
 {
 	write_sysreg(0, hstr_el2);
-	write_sysreg(0, pmuserenr_el0);
+	if (kvm_arm_support_pmu_v3())
+		write_sysreg(0, pmuserenr_el0);
 }
 
 static inline void ___activate_traps(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/nvhe/debug-sr.c

@@ -58,16 +58,24 @@ static void __debug_restore_spe(u64 pmscr_el1)
 	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
 }
 
-void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	/* Disable and flush SPE data generation */
 	__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+}
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
 	__debug_switch_to_guest_common(vcpu);
 }
 
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu)
+{
+	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+}
+
 void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
-	__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
 	__debug_switch_to_host_common(vcpu);
 }
 

arch/arm64/kvm/hyp/nvhe/host.S

@@ -71,7 +71,8 @@ SYM_FUNC_START(__host_enter)
 SYM_FUNC_END(__host_enter)
 
 /*
- * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+ * void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+ * 				  u64 elr, u64 par);
  */
 SYM_FUNC_START(__hyp_do_panic)
 	/* Prepare and exit to the host's panic funciton. */
@@ -82,9 +83,11 @@ SYM_FUNC_START(__hyp_do_panic)
 	hyp_kimg_va lr, x6
 	msr	elr_el2, lr
 
-	/* Set the panic format string. Use the, now free, LR as scratch. */
+	mov	x29, x0
-	ldr	lr, =__hyp_panic_string
+
-	hyp_kimg_va lr, x6
+	/* Load the format string into x0 and arguments into x1-7 */
+	ldr	x0, =__hyp_panic_string
+	hyp_kimg_va x0, x6
 
 	/* Load the format arguments into x1-7. */
 	mov	x6, x3
@@ -94,9 +97,7 @@ SYM_FUNC_START(__hyp_do_panic)
 	mrs	x5, hpfar_el2
 
 	/* Enter the host, conditionally restoring the host context. */
-	cmp	x0, xzr
+	cbz	x29, __host_enter_without_restoring
-	mov	x0, lr
-	b.eq	__host_enter_without_restoring
 	b	__host_enter_for_panic
 SYM_FUNC_END(__hyp_do_panic)
 

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -46,11 +46,11 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
 }
 
-static void handle___kvm_tlb_flush_local_vmid(struct kvm_cpu_context *host_ctxt)
+static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
 
-	__kvm_tlb_flush_local_vmid(kern_hyp_va(mmu));
+	__kvm_flush_cpu_context(kern_hyp_va(mmu));
 }
 
 static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt)
@@ -67,9 +67,9 @@ static void handle___kvm_enable_ssbs(struct kvm_cpu_context *host_ctxt)
 	write_sysreg_el2(tmp, SYS_SCTLR);
 }
 
-static void handle___vgic_v3_get_ich_vtr_el2(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt)
 {
-	cpu_reg(host_ctxt, 1) = __vgic_v3_get_ich_vtr_el2();
+	cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config();
 }
 
 static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt)
@@ -115,10 +115,10 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
-	HANDLE_FUNC(__kvm_tlb_flush_local_vmid),
+	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
 	HANDLE_FUNC(__kvm_enable_ssbs),
-	HANDLE_FUNC(__vgic_v3_get_ich_vtr_el2),
+	HANDLE_FUNC(__vgic_v3_get_gic_config),
 	HANDLE_FUNC(__vgic_v3_read_vmcr),
 	HANDLE_FUNC(__vgic_v3_write_vmcr),
 	HANDLE_FUNC(__vgic_v3_init_lrs),

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -192,6 +192,14 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
 
 	__sysreg_save_state_nvhe(host_ctxt);
+	/*
+	 * We must flush and disable the SPE buffer for nVHE, as
+	 * the translation regime(EL1&0) is going to be loaded with
+	 * that of the guest. And we must do this before we change the
+	 * translation regime to EL2 (via MDCR_EL2_E2PB == 0) and
+	 * before we load guest Stage1.
+	 */
+	__debug_save_host_buffers_nvhe(vcpu);
 
 	__adjust_pc(vcpu);
 
@@ -234,11 +242,12 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
 		__fpsimd_save_fpexc32(vcpu);
 
+	__debug_switch_to_host(vcpu);
 	/*
 	 * This must come after restoring the host sysregs, since a non-VHE
 	 * system may enable SPE here and make use of the TTBRs.
 	 */
-	__debug_switch_to_host(vcpu);
+	__debug_restore_host_buffers_nvhe(vcpu);
 
 	if (pmu_switch_needed)
 		__pmu_switch_to_host(host_ctxt);
@@ -257,7 +266,6 @@ void __noreturn hyp_panic(void)
 	u64 spsr = read_sysreg_el2(SYS_SPSR);
 	u64 elr = read_sysreg_el2(SYS_ELR);
 	u64 par = read_sysreg_par();
-	bool restore_host = true;
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
 
@@ -271,7 +279,7 @@ void __noreturn hyp_panic(void)
 		__sysreg_restore_state_nvhe(host_ctxt);
 	}
 
-	__hyp_do_panic(restore_host, spsr, elr, par);
+	__hyp_do_panic(host_ctxt, spsr, elr, par);
 	unreachable();
 }
 

arch/arm64/kvm/hyp/nvhe/tlb.c

@@ -123,7 +123,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
@@ -131,6 +131,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
+	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 

arch/arm64/kvm/hyp/pgtable.c

@@ -223,6 +223,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 		goto out;
 
 	if (!table) {
+		data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level));
 		data->addr += kvm_granule_size(level);
 		goto out;
 	}

arch/arm64/kvm/hyp/vgic-v3-sr.c

@@ -405,9 +405,45 @@ void __vgic_v3_init_lrs(void)
 		__gic_v3_set_lr(0, i);
 }
 
-u64 __vgic_v3_get_ich_vtr_el2(void)
+/*
+ * Return the GIC CPU configuration:
+ * - [31:0]  ICH_VTR_EL2
+ * - [62:32] RES0
+ * - [63]    MMIO (GICv2) capable
+ */
+u64 __vgic_v3_get_gic_config(void)
 {
-	return read_gicreg(ICH_VTR_EL2);
+	u64 val, sre = read_gicreg(ICC_SRE_EL1);
+	unsigned long flags = 0;
+
+	/*
+	 * To check whether we have a MMIO-based (GICv2 compatible)
+	 * CPU interface, we need to disable the system register
+	 * view. To do that safely, we have to prevent any interrupt
+	 * from firing (which would be deadly).
+	 *
+	 * Note that this only makes sense on VHE, as interrupts are
+	 * already masked for nVHE as part of the exception entry to
+	 * EL2.
+	 */
+	if (has_vhe())
+		flags = local_daif_save();
+
+	write_gicreg(0, ICC_SRE_EL1);
+	isb();
+
+	val = read_gicreg(ICC_SRE_EL1);
+
+	write_gicreg(sre, ICC_SRE_EL1);
+	isb();
+
+	if (has_vhe())
+		local_daif_restore(flags);
+
+	val  = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
+	val |= read_gicreg(ICH_VTR_EL2);
+
+	return val;
 }
 
 u64 __vgic_v3_read_vmcr(void)

arch/arm64/kvm/hyp/vhe/tlb.c

@@ -127,7 +127,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_host(&cxt);
 }
 
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
 
@@ -135,6 +135,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
+	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 

arch/arm64/kvm/mmu.c

@@ -1312,8 +1312,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	 * Prevent userspace from creating a memory region outside of the IPA
 	 * space addressable by the KVM guest IPA space.
 	 */
-	if (memslot->base_gfn + memslot->npages >=
+	if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
-	    (kvm_phys_size(kvm) >> PAGE_SHIFT))
 		return -EFAULT;
 
 	mmap_read_lock(current->mm);

arch/arm64/kvm/perf.c

@@ -11,6 +11,8 @@
 
 #include <asm/kvm_emulate.h>
 
+DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
 static int kvm_is_in_guest(void)
 {
         return kvm_get_running_vcpu() != NULL;
@@ -48,6 +50,14 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
 
 int kvm_perf_init(void)
 {
+	/*
+	 * Check if HW_PERF_EVENTS are supported by checking the number of
+	 * hardware performance counters. This could ensure the presence of
+	 * a physical PMU and CONFIG_PERF_EVENT is selected.
+	 */
+	if (IS_ENABLED(CONFIG_ARM_PMU) && perf_num_counters() > 0)
+		static_branch_enable(&kvm_arm_pmu_available);
+
 	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
 }
 

arch/arm64/kvm/pmu-emul.c

@@ -823,16 +823,6 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	return val & mask;
 }
 
-bool kvm_arm_support_pmu_v3(void)
-{
-	/*
-	 * Check if HW_PERF_EVENTS are supported by checking the number of
-	 * hardware performance counters. This could ensure the presence of
-	 * a physical PMU and CONFIG_PERF_EVENT is selected.
-	 */
-	return (perf_num_counters() > 0);
-}
-
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
 	if (!kvm_vcpu_has_pmu(vcpu))

arch/arm64/kvm/reset.c

@@ -311,23 +311,24 @@ int kvm_set_ipa_limit(void)
 	}
 
 	switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
-	default:
+	case ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE:
-	case 1:
 		kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
 		return -EINVAL;
-	case 0:
+	case ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT:
 		kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
 		break;
-	case 2:
+	case ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX:
 		kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
 		break;
+	default:
+		kvm_err("Unsupported value for TGRAN_2, giving up\n");
+		return -EINVAL;
 	}
 
 	kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
-	WARN(kvm_ipa_limit < KVM_PHYS_SHIFT,
+	kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit,
-	     "KVM IPA Size Limit (%d bits) is smaller than default size\n",
+		 ((kvm_ipa_limit < KVM_PHYS_SHIFT) ?
-	     kvm_ipa_limit);
+		  " (Reduced IPA size, limited VM/VMM compatibility)" : ""));
-	kvm_info("IPA Size Limit: %d bits\n", kvm_ipa_limit);
 
 	return 0;
 }
@@ -356,6 +357,11 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 			return -EINVAL;
 	} else {
 		phys_shift = KVM_PHYS_SHIFT;
+		if (phys_shift > kvm_ipa_limit) {
+			pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
+				     current->comm);
+			return -EINVAL;
+		}
 	}
 
 	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);

arch/arm64/kvm/vgic/vgic-v3.c

@@ -574,9 +574,13 @@ early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable);
  */
 int vgic_v3_probe(const struct gic_kvm_info *info)
 {
-	u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2);
+	u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
+	bool has_v2;
 	int ret;
 
+	has_v2 = ich_vtr_el2 >> 63;
+	ich_vtr_el2 = (u32)ich_vtr_el2;
+
 	/*
 	 * The ListRegs field is 5 bits, but there is an architectural
 	 * maximum of 16 list registers. Just ignore bit 4...
@@ -594,13 +598,15 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 			 gicv4_enable ? "en" : "dis");
 	}
 
+	kvm_vgic_global_state.vcpu_base = 0;
+
 	if (!info->vcpu.start) {
 		kvm_info("GICv3: no GICV resource entry\n");
-		kvm_vgic_global_state.vcpu_base = 0;
+	} else if (!has_v2) {
+		pr_warn(FW_BUG "CPU interface incapable of MMIO access\n");
 	} else if (!PAGE_ALIGNED(info->vcpu.start)) {
 		pr_warn("GICV physical address 0x%llx not page aligned\n",
 			(unsigned long long)info->vcpu.start);
-		kvm_vgic_global_state.vcpu_base = 0;
 	} else {
 		kvm_vgic_global_state.vcpu_base = info->vcpu.start;
 		kvm_vgic_global_state.can_emulate_gicv2 = true;

arch/arm64/mm/init.c

@@ -219,17 +219,40 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 int pfn_valid(unsigned long pfn)
 {
-	phys_addr_t addr = pfn << PAGE_SHIFT;
+	phys_addr_t addr = PFN_PHYS(pfn);
 
-	if ((addr >> PAGE_SHIFT) != pfn)
+	/*
+	 * Ensure the upper PAGE_SHIFT bits are clear in the
+	 * pfn. Else it might lead to false positives when
+	 * some of the upper bits are set, but the lower bits
+	 * match a valid pfn.
+	 */
+	if (PHYS_PFN(addr) != pfn)
 		return 0;
 
 #ifdef CONFIG_SPARSEMEM
+{
+	struct mem_section *ms;
+
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 
-	if (!valid_section(__pfn_to_section(pfn)))
+	ms = __pfn_to_section(pfn);
+	if (!valid_section(ms))
 		return 0;
+
+	/*
+	 * ZONE_DEVICE memory does not have the memblock entries.
+	 * memblock_is_map_memory() check for ZONE_DEVICE based
+	 * addresses will always fail. Even the normal hotplugged
+	 * memory will never have MEMBLOCK_NOMAP flag set in their
+	 * memblock entries. Skip memblock search for all non early
+	 * memory sections covering all of hotplug memory including
+	 * both normal and ZONE_DEVICE based.
+	 */
+	if (!early_section(ms))
+		return pfn_section_valid(ms, pfn);
+}
 #endif
 	return memblock_is_map_memory(addr);
 }

arch/arm64/mm/mmu.c

@@ -40,7 +40,7 @@
 #define NO_BLOCK_MAPPINGS	BIT(0)
 #define NO_CONT_MAPPINGS	BIT(1)
 
-u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN);
 u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 
 u64 __section(".mmuoff.data.write") vabits_actual;
@@ -512,7 +512,8 @@ static void __init map_mem(pgd_t *pgdp)
 		 * if MTE is present. Otherwise, it has the same attributes as
 		 * PAGE_KERNEL.
 		 */
-		__map_memblock(pgdp, start, end, PAGE_KERNEL_TAGGED, flags);
+		__map_memblock(pgdp, start, end, pgprot_tagged(PAGE_KERNEL),
+			       flags);
 	}
 
 	/*

arch/ia64/include/asm/syscall.h

@@ -32,7 +32,7 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	return regs->r10 == -1 ? regs->r8:0;
+	return regs->r10 == -1 ? -regs->r8:0;
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,

arch/ia64/kernel/ptrace.c

@@ -2013,27 +2013,39 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data)
 {
 	struct syscall_get_set_args *args = data;
 	struct pt_regs *pt = args->regs;
-	unsigned long *krbs, cfm, ndirty;
+	unsigned long *krbs, cfm, ndirty, nlocals, nouts;
 	int i, count;
 
 	if (unw_unwind_to_user(info) < 0)
 		return;
 
+	/*
+	 * We get here via a few paths:
+	 * - break instruction: cfm is shared with caller.
+	 *   syscall args are in out= regs, locals are non-empty.
+	 * - epsinstruction: cfm is set by br.call
+	 *   locals don't exist.
+	 *
+	 * For both cases argguments are reachable in cfm.sof - cfm.sol.
+	 * CFM: [ ... | sor: 17..14 | sol : 13..7 | sof : 6..0 ]
+	 */
 	cfm = pt->cr_ifs;
+	nlocals = (cfm >> 7) & 0x7f; /* aka sol */
+	nouts = (cfm & 0x7f) - nlocals; /* aka sof - sol */
 	krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8;
 	ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19));
 
 	count = 0;
 	if (in_syscall(pt))
-		count = min_t(int, args->n, cfm & 0x7f);
+		count = min_t(int, args->n, nouts);
 
+	/* Iterate over outs. */
 	for (i = 0; i < count; i++) {
+		int j = ndirty + nlocals + i + args->i;
 		if (args->rw)
-			*ia64_rse_skip_regs(krbs, ndirty + i + args->i) =
+			*ia64_rse_skip_regs(krbs, j) = args->args[i];
-				args->args[i];
 		else
-			args->args[i] = *ia64_rse_skip_regs(krbs,
+			args->args[i] = *ia64_rse_skip_regs(krbs, j);
-				ndirty + i + args->i);
 	}
 
 	if (!args->rw) {

arch/m68k/include/asm/page_mm.h

@@ -171,7 +171,7 @@ static inline __attribute_const__ int __virt_to_node_shift(void)
 #include <asm-generic/memory_model.h>
 #endif
 
-#define virt_addr_valid(kaddr)	((void *)(kaddr) >= (void *)PAGE_OFFSET && (void *)(kaddr) < high_memory)
+#define virt_addr_valid(kaddr)	((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory)
 #define pfn_valid(pfn)		virt_addr_valid(pfn_to_virt(pfn))
 
 #endif /* __ASSEMBLY__ */

arch/m68k/include/asm/page_no.h

@@ -30,8 +30,8 @@ extern unsigned long memory_end;
 #define page_to_pfn(page)	virt_to_pfn(page_to_virt(page))
 #define pfn_valid(pfn)	        ((pfn) < max_mapnr)
 
-#define	virt_addr_valid(kaddr)	(((void *)(kaddr) >= (void *)PAGE_OFFSET) && \
+#define	virt_addr_valid(kaddr)	(((unsigned long)(kaddr) >= PAGE_OFFSET) && \
-				((void *)(kaddr) < (void *)memory_end))
+				((unsigned long)(kaddr) < memory_end))
 
 #endif /* __ASSEMBLY__ */
 

arch/mips/boot/compressed/decompress.c

@@ -14,6 +14,7 @@
 
 #include <asm/addrspace.h>
 #include <asm/unaligned.h>
+#include <asm-generic/vmlinux.lds.h>
 
 /*
  * These two variables specify the free mem region
@@ -120,6 +121,13 @@ void decompress_kernel(unsigned long boot_heap_start)
 		/* last four bytes is always image size in little endian */
 		image_size = get_unaligned_le32((void *)&__image_end - 4);
 
+		/* The device tree's address must be properly aligned  */
+		image_size = ALIGN(image_size, STRUCT_ALIGNMENT);
+
+		puts("Copy device tree to address  ");
+		puthex(VMLINUX_LOAD_ADDRESS_ULL + image_size);
+		puts("\n");
+
 		/* copy dtb to where the booted kernel will expect it */
 		memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size,
 		       __appended_dtb, dtb_size);

arch/mips/crypto/Makefile

@@ -12,8 +12,8 @@ AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots
 obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o
 poly1305-mips-y := poly1305-core.o poly1305-glue.o
 
-perlasm-flavour-$(CONFIG_CPU_MIPS32) := o32
+perlasm-flavour-$(CONFIG_32BIT) := o32
-perlasm-flavour-$(CONFIG_CPU_MIPS64) := 64
+perlasm-flavour-$(CONFIG_64BIT) := 64
 
 quiet_cmd_perlasm = PERLASM $@
       cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@)

arch/mips/include/asm/traps.h

@@ -24,8 +24,11 @@ extern void (*board_ebase_setup)(void);
 extern void (*board_cache_error_setup)(void);
 
 extern int register_nmi_notifier(struct notifier_block *nb);
+extern void reserve_exception_space(phys_addr_t addr, unsigned long size);
 extern char except_vec_nmi[];
 
+#define VECTORSPACING 0x100	/* for EI/VI mode */
+
 #define nmi_notifier(fn, pri)						\
 ({									\
 	static struct notifier_block fn##_nb = {			\

arch/mips/kernel/cpu-probe.c

@@ -26,6 +26,7 @@
 #include <asm/elf.h>
 #include <asm/pgtable-bits.h>
 #include <asm/spram.h>
+#include <asm/traps.h>
 #include <linux/uaccess.h>
 
 #include "fpu-probe.h"
@@ -1628,6 +1629,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 		c->cputype = CPU_BMIPS3300;
 		__cpu_name[cpu] = "Broadcom BMIPS3300";
 		set_elf_platform(cpu, "bmips3300");
+		reserve_exception_space(0x400, VECTORSPACING * 64);
 		break;
 	case PRID_IMP_BMIPS43XX: {
 		int rev = c->processor_id & PRID_REV_MASK;
@@ -1638,6 +1640,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 			__cpu_name[cpu] = "Broadcom BMIPS4380";
 			set_elf_platform(cpu, "bmips4380");
 			c->options |= MIPS_CPU_RIXI;
+			reserve_exception_space(0x400, VECTORSPACING * 64);
 		} else {
 			c->cputype = CPU_BMIPS4350;
 			__cpu_name[cpu] = "Broadcom BMIPS4350";
@@ -1654,6 +1657,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 			__cpu_name[cpu] = "Broadcom BMIPS5000";
 		set_elf_platform(cpu, "bmips5000");
 		c->options |= MIPS_CPU_ULRI | MIPS_CPU_RIXI;
+		reserve_exception_space(0x1000, VECTORSPACING * 64);
 		break;
 	}
 }
@@ -2133,6 +2137,8 @@ void cpu_probe(void)
 	if (cpu == 0)
 		__ua_limit = ~((1ull << cpu_vmbits) - 1);
 #endif
+
+	reserve_exception_space(0, 0x1000);
 }
 
 void cpu_report(void)

arch/mips/kernel/cpu-r3k-probe.c

@@ -21,6 +21,7 @@
 #include <asm/fpu.h>
 #include <asm/mipsregs.h>
 #include <asm/elf.h>
+#include <asm/traps.h>
 
 #include "fpu-probe.h"
 
@@ -158,6 +159,8 @@ void cpu_probe(void)
 		cpu_set_fpu_opts(c);
 	else
 		cpu_set_nofpu_opts(c);
+
+	reserve_exception_space(0, 0x400);
 }
 
 void cpu_report(void)

arch/mips/kernel/traps.c

@@ -2009,13 +2009,16 @@ void __noreturn nmi_exception_handler(struct pt_regs *regs)
 	nmi_exit();
 }
 
-#define VECTORSPACING 0x100	/* for EI/VI mode */
-
 unsigned long ebase;
 EXPORT_SYMBOL_GPL(ebase);
 unsigned long exception_handlers[32];
 unsigned long vi_handlers[64];
 
+void reserve_exception_space(phys_addr_t addr, unsigned long size)
+{
+	memblock_reserve(addr, size);
+}
+
 void __init *set_except_vector(int n, void *addr)
 {
 	unsigned long handler = (unsigned long) addr;
@@ -2367,10 +2370,7 @@ void __init trap_init(void)
 
 	if (!cpu_has_mips_r2_r6) {
 		ebase = CAC_BASE;
-		ebase_pa = virt_to_phys((void *)ebase);
 		vec_size = 0x400;
-
-		memblock_reserve(ebase_pa, vec_size);
 	} else {
 		if (cpu_has_veic || cpu_has_vint)
 			vec_size = 0x200 + VECTORSPACING*64;

arch/mips/kernel/vmlinux.lds.S

@@ -145,6 +145,7 @@ SECTIONS
 	}
 
 #ifdef CONFIG_MIPS_ELF_APPENDED_DTB
+	STRUCT_ALIGN();
 	.appended_dtb : AT(ADDR(.appended_dtb) - LOAD_OFFSET) {
 		*(.appended_dtb)
 		KEEP(*(.appended_dtb))
@@ -172,6 +173,11 @@ SECTIONS
 #endif
 
 #ifdef CONFIG_MIPS_RAW_APPENDED_DTB
+	.fill : {
+		FILL(0);
+		BYTE(0);
+		. = ALIGN(8);
+	}
 	__appended_dtb = .;
 	/* leave space for appended DTB */
 	. += 0x100000;

arch/parisc/Kconfig

@@ -203,9 +203,12 @@ config PREFETCH
 	def_bool y
 	depends on PA8X00 || PA7200
 
+config PARISC_HUGE_KERNEL
+	def_bool y if !MODULES || UBSAN || FTRACE || COMPILE_TEST
+
 config MLONGCALLS
-	def_bool y if !MODULES || UBSAN || FTRACE
+	def_bool y if PARISC_HUGE_KERNEL
-	bool "Enable the -mlong-calls compiler option for big kernels" if MODULES && !UBSAN && !FTRACE
+	bool "Enable the -mlong-calls compiler option for big kernels" if !PARISC_HUGE_KERNEL
 	depends on PA8X00
 	help
 	  If you configure the kernel to include many drivers built-in instead

arch/parisc/kernel/ptrace.c

@@ -567,8 +567,6 @@ static const struct user_regset_view user_parisc_native_view = {
 };
 
 #ifdef CONFIG_64BIT
-#include <linux/compat.h>
-
 static int gpr32_get(struct task_struct *target,
 		     const struct user_regset *regset,
 		     struct membuf to)

arch/powerpc/include/asm/code-patching.h

@@ -73,9 +73,10 @@ void __patch_exception(int exc, unsigned long addr);
 #endif
 
 #define OP_RT_RA_MASK	0xffff0000UL
-#define LIS_R2		0x3c020000UL
+#define LIS_R2		(PPC_INST_ADDIS | __PPC_RT(R2))
-#define ADDIS_R2_R12	0x3c4c0000UL
+#define ADDIS_R2_R12	(PPC_INST_ADDIS | __PPC_RT(R2) | __PPC_RA(R12))
-#define ADDI_R2_R2	0x38420000UL
+#define ADDI_R2_R2	(PPC_INST_ADDI  | __PPC_RT(R2) | __PPC_RA(R2))
+
 
 static inline unsigned long ppc_function_entry(void *func)
 {

arch/powerpc/include/asm/dcr-native.h

@@ -53,8 +53,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
 #define mfdcr(rn)						\
 	({unsigned int rval;					\
 	if (__builtin_constant_p(rn) && rn < 1024)		\
-		asm volatile("mfdcr %0," __stringify(rn)	\
+		asm volatile("mfdcr %0, %1" : "=r" (rval)	\
-		              : "=r" (rval));			\
+			      : "n" (rn));			\
 	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
 		rval = mfdcrx(rn);				\
 	else							\
@@ -64,8 +64,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
 #define mtdcr(rn, v)						\
 do {								\
 	if (__builtin_constant_p(rn) && rn < 1024)		\
-		asm volatile("mtdcr " __stringify(rn) ",%0"	\
+		asm volatile("mtdcr %0, %1"			\
-			      : : "r" (v)); 			\
+			      : : "n" (rn), "r" (v));		\
 	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
 		mtdcrx(rn, v);					\
 	else							\

arch/powerpc/include/asm/interrupt.h

@@ -410,7 +410,6 @@ DECLARE_INTERRUPT_HANDLER(altivec_assist_exception);
 DECLARE_INTERRUPT_HANDLER(CacheLockingException);
 DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException);
 DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException);
-DECLARE_INTERRUPT_HANDLER(unrecoverable_exception);
 DECLARE_INTERRUPT_HANDLER(WatchdogException);
 DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
 
@@ -437,6 +436,8 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
 
 DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
 
+void unrecoverable_exception(struct pt_regs *regs);
+
 void replay_system_reset(void);
 void replay_soft_interrupts(void);
 

arch/powerpc/include/asm/mmu.h

@@ -228,7 +228,7 @@ enum {
 #define MMU_FTRS_ALWAYS		0
 #endif
 
-static inline bool early_mmu_has_feature(unsigned long feature)
+static __always_inline bool early_mmu_has_feature(unsigned long feature)
 {
 	if (MMU_FTRS_ALWAYS & feature)
 		return true;
@@ -286,7 +286,7 @@ static inline void mmu_feature_keys_init(void)
 
 }
 
-static inline bool mmu_has_feature(unsigned long feature)
+static __always_inline bool mmu_has_feature(unsigned long feature)
 {
 	return early_mmu_has_feature(feature);
 }

arch/powerpc/include/asm/ptrace.h

@@ -195,7 +195,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
 #define TRAP_FLAGS_MASK		0x11
 #define TRAP(regs)		((regs)->trap & ~TRAP_FLAGS_MASK)
 #define FULL_REGS(regs)		(((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs)	((regs)->trap |= 1)
+#define SET_FULL_REGS(regs)	((regs)->trap &= ~1)
 #endif
 #define CHECK_FULL_REGS(regs)	BUG_ON(!FULL_REGS(regs))
 #define NV_REG_POISON		0xdeadbeefdeadbeefUL
@@ -210,7 +210,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
 #define TRAP_FLAGS_MASK		0x1F
 #define TRAP(regs)		((regs)->trap & ~TRAP_FLAGS_MASK)
 #define FULL_REGS(regs)		(((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs)	((regs)->trap |= 1)
+#define SET_FULL_REGS(regs)	((regs)->trap &= ~1)
 #define IS_CRITICAL_EXC(regs)	(((regs)->trap & 2) != 0)
 #define IS_MCHECK_EXC(regs)	(((regs)->trap & 4) != 0)
 #define IS_DEBUG_EXC(regs)	(((regs)->trap & 8) != 0)

arch/powerpc/include/asm/switch_to.h

@@ -71,6 +71,16 @@ static inline void disable_kernel_vsx(void)
 {
 	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
 }
+#else
+static inline void enable_kernel_vsx(void)
+{
+	BUILD_BUG();
+}
+
+static inline void disable_kernel_vsx(void)
+{
+	BUILD_BUG();
+}
 #endif
 
 #ifdef CONFIG_SPE

arch/powerpc/include/asm/vio.h

@@ -113,7 +113,7 @@ struct vio_driver {
 	const char *name;
 	const struct vio_device_id *id_table;
 	int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
-	int (*remove)(struct vio_dev *dev);
+	void (*remove)(struct vio_dev *dev);
 	/* A driver must have a get_desired_dma() function to
 	 * be loaded in a CMO environment if it uses DMA.
 	 */

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

@@ -466,7 +466,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 
 	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
 	/* MSR[RI] is clear iff using SRR regs */
-	.if IHSRR == EXC_HV_OR_STD
+	.if IHSRR_IF_HVMODE
 	BEGIN_FTR_SECTION
 	xori	r10,r10,MSR_RI
 	END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)

arch/powerpc/kernel/head_book3s_32.S

@@ -457,11 +457,12 @@ InstructionTLBMiss:
 	cmplw	0,r1,r3
 #endif
 	mfspr	r2, SPRN_SDR1
-	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
 	rlwinm	r2, r2, 28, 0xfffff000
 #ifdef CONFIG_MODULES
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 #endif
 112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
@@ -520,10 +521,11 @@ DataLoadTLBMiss:
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SDR1
-	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED
+	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
 	rlwinm	r2, r2, 28, 0xfffff000
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
 	lwz	r2,0(r2)		/* get pmd entry */
@@ -597,10 +599,11 @@ DataStoreTLBMiss:
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SDR1
-	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
+	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
 	rlwinm	r2, r2, 28, 0xfffff000
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
 	lwz	r2,0(r2)		/* get pmd entry */

arch/powerpc/kernel/interrupt.c

@@ -149,7 +149,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
  * enabled when the interrupt handler returns (indicating a process-context /
  * synchronous interrupt) then irqs_enabled should be true.
  */
-static notrace inline bool __prep_irq_for_enabled_exit(bool clear_ri)
+static notrace __always_inline bool __prep_irq_for_enabled_exit(bool clear_ri)
 {
 	/* This must be done with RI=1 because tracing may touch vmaps */
 	trace_hardirqs_on();
@@ -436,7 +436,6 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	return ret;
 }
 
-void unrecoverable_exception(struct pt_regs *regs);
 void preempt_schedule_irq(void);
 
 notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr)

arch/powerpc/kernel/traps.c

@@ -2170,7 +2170,7 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
  * in the MSR is 0.  This indicates that SRR0/1 are live, and that
  * we therefore lost state by taking this exception.
  */
-DEFINE_INTERRUPT_HANDLER(unrecoverable_exception)
+void unrecoverable_exception(struct pt_regs *regs)
 {
 	pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
 		 regs->trap, regs->nip, regs->msr);

arch/powerpc/lib/sstep.c

@@ -904,7 +904,7 @@ static nokprobe_inline int do_vsx_load(struct instruction_op *op,
 	if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs))
 		return -EFAULT;
 
-	nr_vsx_regs = size / sizeof(__vector128);
+	nr_vsx_regs = max(1ul, size / sizeof(__vector128));
 	emulate_vsx_load(op, buf, mem, cross_endian);
 	preempt_disable();
 	if (reg < 32) {
@@ -951,7 +951,7 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op,
 	if (!address_ok(regs, ea, size))
 		return -EFAULT;
 
-	nr_vsx_regs = size / sizeof(__vector128);
+	nr_vsx_regs = max(1ul, size / sizeof(__vector128));
 	preempt_disable();
 	if (reg < 32) {
 		/* FP regs + extensions */

arch/powerpc/perf/core-book3s.c

@@ -222,7 +222,7 @@ static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *
 	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
 		*addrp = mfspr(SPRN_SDAR);
 
-	if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0)
+	if (is_kernel_addr(mfspr(SPRN_SDAR)) && event->attr.exclude_kernel)
 		*addrp = 0;
 }
 
@@ -507,7 +507,7 @@ static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *
 			 * addresses, hence include a check before filtering code
 			 */
 			if (!(ppmu->flags & PPMU_ARCH_31) &&
-				is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
+			    is_kernel_addr(addr) && event->attr.exclude_kernel)
 				continue;
 
 			/* Branches are read most recent first (ie. mfbhrb 0 is

arch/powerpc/platforms/pseries/msi.c

@@ -4,6 +4,7 @@
  * Copyright 2006-2007 Michael Ellerman, IBM Corp.
  */
 
+#include <linux/crash_dump.h>
 #include <linux/device.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
@@ -458,8 +459,28 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 			return hwirq;
 		}
 
-		virq = irq_create_mapping_affinity(NULL, hwirq,
+		/*
-						   entry->affinity);
+		 * Depending on the number of online CPUs in the original
+		 * kernel, it is likely for CPU #0 to be offline in a kdump
+		 * kernel. The associated IRQs in the affinity mappings
+		 * provided by irq_create_affinity_masks() are thus not
+		 * started by irq_startup(), as per-design for managed IRQs.
+		 * This can be a problem with multi-queue block devices driven
+		 * by blk-mq : such a non-started IRQ is very likely paired
+		 * with the single queue enforced by blk-mq during kdump (see
+		 * blk_mq_alloc_tag_set()). This causes the device to remain
+		 * silent and likely hangs the guest at some point.
+		 *
+		 * We don't really care for fine-grained affinity when doing
+		 * kdump actually : simply ignore the pre-computed affinity
+		 * masks in this case and let the default mask with all CPUs
+		 * be used when creating the IRQ mappings.
+		 */
+		if (is_kdump_kernel())
+			virq = irq_create_mapping(NULL, hwirq);
+		else
+			virq = irq_create_mapping_affinity(NULL, hwirq,
+							   entry->affinity);
 
 		if (!virq) {
 			pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);

arch/powerpc/platforms/pseries/vio.c

@@ -1261,7 +1261,6 @@ static int vio_bus_remove(struct device *dev)
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct vio_driver *viodrv = to_vio_driver(dev->driver);
 	struct device *devptr;
-	int ret = 1;
 
 	/*
 	 * Hold a reference to the device after the remove function is called
@@ -1270,13 +1269,13 @@ static int vio_bus_remove(struct device *dev)
 	devptr = get_device(dev);
 
 	if (viodrv->remove)
-		ret = viodrv->remove(viodev);
+		viodrv->remove(viodev);
 
-	if (!ret && firmware_has_feature(FW_FEATURE_CMO))
+	if (firmware_has_feature(FW_FEATURE_CMO))
 		vio_cmo_bus_remove(viodev);
 
 	put_device(devptr);
-	return ret;
+	return 0;
 }
 
 /**

arch/s390/configs/debug_defconfig

@@ -275,9 +275,9 @@ CONFIG_IP_VS_DH=m
 CONFIG_IP_VS_SH=m
 CONFIG_IP_VS_SED=m
 CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_TWOS=m
 CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_IP_NF_IPTABLES=m
@@ -298,7 +298,6 @@ CONFIG_IP_NF_SECURITY=m
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_TABLES_IPV6=y
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
@@ -481,7 +480,6 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
@@ -581,7 +579,6 @@ CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
-# CONFIG_SURFACE_PLATFORMS is not set
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -635,6 +632,7 @@ CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -714,12 +712,8 @@ CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
@@ -731,7 +725,6 @@ CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4=m
@@ -796,12 +789,9 @@ CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
 CONFIG_SLUB_DEBUG_ON=y
 CONFIG_SLUB_STATS=y
-CONFIG_DEBUG_KMEMLEAK=y
-CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_VM=y
 CONFIG_DEBUG_VM_VMACACHE=y
-CONFIG_DEBUG_VM_RB=y
 CONFIG_DEBUG_VM_PGFLAGS=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
@@ -838,6 +828,7 @@ CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_FTRACE_STARTUP_TEST=y
 # CONFIG_EVENT_TRACE_STARTUP_TEST is not set
+CONFIG_DEBUG_ENTRY=y
 CONFIG_NOTIFIER_ERROR_INJECTION=m
 CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
 CONFIG_FAULT_INJECTION=y
@@ -861,4 +852,3 @@ CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
-CONFIG_DEBUG_ENTRY=y

arch/s390/configs/defconfig

@@ -266,9 +266,9 @@ CONFIG_IP_VS_DH=m
 CONFIG_IP_VS_SH=m
 CONFIG_IP_VS_SED=m
 CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_TWOS=m
 CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_IP_NF_IPTABLES=m
@@ -289,7 +289,6 @@ CONFIG_IP_NF_SECURITY=m
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_TABLES_IPV6=y
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
@@ -473,7 +472,6 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
@@ -573,7 +571,6 @@ CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
-# CONFIG_SURFACE_PLATFORMS is not set
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -623,6 +620,7 @@ CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
 CONFIG_HUGETLBFS=y
 CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
@@ -703,12 +701,8 @@ CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
 CONFIG_CRYPTO_ANUBIS=m
@@ -720,7 +714,6 @@ CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4=m

arch/s390/configs/zfcpdump_defconfig

@@ -26,7 +26,6 @@ CONFIG_CRASH_DUMP=y
 # CONFIG_SECCOMP is not set
 # CONFIG_GCC_PLUGINS is not set
 CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_COMPACTION is not set
 # CONFIG_MIGRATION is not set
@@ -61,11 +60,9 @@ CONFIG_RAW_DRIVER=y
 # CONFIG_HID is not set
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_VHOST_MENU is not set
-# CONFIG_SURFACE_PLATFORMS is not set
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
-CONFIG_CONFIGFS_FS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"

arch/s390/include/asm/idle.h

@@ -14,12 +14,12 @@
 
 struct s390_idle_data {
 	seqcount_t seqcount;
-	unsigned long long idle_count;
+	unsigned long idle_count;
-	unsigned long long idle_time;
+	unsigned long idle_time;
-	unsigned long long clock_idle_enter;
+	unsigned long clock_idle_enter;
-	unsigned long long clock_idle_exit;
+	unsigned long clock_idle_exit;
-	unsigned long long timer_idle_enter;
+	unsigned long timer_idle_enter;
-	unsigned long long timer_idle_exit;
+	unsigned long timer_idle_exit;
 	unsigned long mt_cycles_enter[8];
 };
 

arch/s390/include/asm/timex.h

@@ -98,10 +98,10 @@ extern unsigned char ptff_function_mask[16];
 
 /* Query TOD offset result */
 struct ptff_qto {
-	unsigned long long physical_clock;
+	unsigned long physical_clock;
-	unsigned long long tod_offset;
+	unsigned long tod_offset;
-	unsigned long long logical_tod_offset;
+	unsigned long logical_tod_offset;
-	unsigned long long tod_epoch_difference;
+	unsigned long tod_epoch_difference;
 } __packed;
 
 static inline int ptff_query(unsigned int nr)
@@ -151,9 +151,9 @@ struct ptff_qui {
 	rc;								\
 })
 
-static inline unsigned long long local_tick_disable(void)
+static inline unsigned long local_tick_disable(void)
 {
-	unsigned long long old;
+	unsigned long old;
 
 	old = S390_lowcore.clock_comparator;
 	S390_lowcore.clock_comparator = clock_comparator_max;
@@ -161,7 +161,7 @@ static inline unsigned long long local_tick_disable(void)
 	return old;
 }
 
-static inline void local_tick_enable(unsigned long long comp)
+static inline void local_tick_enable(unsigned long comp)
 {
 	S390_lowcore.clock_comparator = comp;
 	set_clock_comparator(S390_lowcore.clock_comparator);
@@ -169,9 +169,9 @@ static inline void local_tick_enable(unsigned long long comp)
 
 #define CLOCK_TICK_RATE		1193180 /* Underlying HZ */
 
-typedef unsigned long long cycles_t;
+typedef unsigned long cycles_t;
 
-static inline unsigned long long get_tod_clock(void)
+static inline unsigned long get_tod_clock(void)
 {
 	union tod_clock clk;
 
@@ -179,10 +179,10 @@ static inline unsigned long long get_tod_clock(void)
 	return clk.tod;
 }
 
-static inline unsigned long long get_tod_clock_fast(void)
+static inline unsigned long get_tod_clock_fast(void)
 {
 #ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
-	unsigned long long clk;
+	unsigned long clk;
 
 	asm volatile("stckf %0" : "=Q" (clk) : : "cc");
 	return clk;
@@ -208,9 +208,9 @@ extern union tod_clock tod_clock_base;
  * Therefore preemption must be disabled, otherwise the returned
  * value is not guaranteed to be monotonic.
  */
-static inline unsigned long long get_tod_clock_monotonic(void)
+static inline unsigned long get_tod_clock_monotonic(void)
 {
-	unsigned long long tod;
+	unsigned long tod;
 
 	preempt_disable_notrace();
 	tod = get_tod_clock() - tod_clock_base.tod;
@@ -237,7 +237,7 @@ static inline unsigned long long get_tod_clock_monotonic(void)
  * -> ns = (th * 125) + ((tl * 125) >> 9);
  *
  */
-static inline unsigned long long tod_to_ns(unsigned long long todval)
+static inline unsigned long tod_to_ns(unsigned long todval)
 {
 	return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9);
 }
@@ -249,10 +249,10 @@ static inline unsigned long long tod_to_ns(unsigned long long todval)
  *
  * Returns: true if a is later than b
  */
-static inline int tod_after(unsigned long long a, unsigned long long b)
+static inline int tod_after(unsigned long a, unsigned long b)
 {
 	if (MACHINE_HAS_SCC)
-		return (long long) a > (long long) b;
+		return (long) a > (long) b;
 	return a > b;
 }
 
@@ -263,10 +263,10 @@ static inline int tod_after(unsigned long long a, unsigned long long b)
  *
  * Returns: true if a is later than b
  */
-static inline int tod_after_eq(unsigned long long a, unsigned long long b)
+static inline int tod_after_eq(unsigned long a, unsigned long b)
 {
 	if (MACHINE_HAS_SCC)
-		return (long long) a >= (long long) b;
+		return (long) a >= (long) b;
 	return a >= b;
 }
 

arch/s390/kernel/idle.c

@@ -47,7 +47,7 @@ void account_idle_time_irq(void)
 void arch_cpu_idle(void)
 {
 	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
-	unsigned long long idle_time;
+	unsigned long idle_time;
 	unsigned long psw_mask;
 
 	/* Wait for external, I/O or machine check interrupt. */
@@ -73,7 +73,7 @@ static ssize_t show_idle_count(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long idle_count;
+	unsigned long idle_count;
 	unsigned int seq;
 
 	do {
@@ -82,14 +82,14 @@ static ssize_t show_idle_count(struct device *dev,
 		if (READ_ONCE(idle->clock_idle_enter))
 			idle_count++;
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-	return sprintf(buf, "%llu\n", idle_count);
+	return sprintf(buf, "%lu\n", idle_count);
 }
 DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
 
 static ssize_t show_idle_time(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
+	unsigned long now, idle_time, idle_enter, idle_exit, in_idle;
 	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
 	unsigned int seq;
 
@@ -109,14 +109,14 @@ static ssize_t show_idle_time(struct device *dev,
 		}
 	}
 	idle_time += in_idle;
-	return sprintf(buf, "%llu\n", idle_time >> 12);
+	return sprintf(buf, "%lu\n", idle_time >> 12);
 }
 DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
 u64 arch_cpu_idle_time(int cpu)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
-	unsigned long long now, idle_enter, idle_exit, in_idle;
+	unsigned long now, idle_enter, idle_exit, in_idle;
 	unsigned int seq;
 
 	do {

arch/s390/kernel/perf_cpum_cf.c

@@ -269,7 +269,7 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 	case CPUMF_CTR_SET_MAX:
 		/* The counter could not be associated to a counter set */
 		return -EINVAL;
-	};
+	}
 
 	/* Initialize for using the CPU-measurement counter facility */
 	if (!atomic_inc_not_zero(&num_events)) {

arch/s390/kernel/perf_cpum_cf_diag.c

@@ -26,12 +26,10 @@
 #include <asm/timex.h>
 #include <asm/debug.h>
 
-#include <asm/perf_cpum_cf_diag.h>
+#include <asm/hwctrset.h>
 
 #define	CF_DIAG_CTRSET_DEF		0xfeef	/* Counter set header mark */
-#define CF_DIAG_MIN_INTERVAL		60	/* Minimum counter set read */
 						/* interval in seconds */
-static unsigned long cf_diag_interval = CF_DIAG_MIN_INTERVAL;
 static unsigned int cf_diag_cpu_speed;
 static debug_info_t *cf_diag_dbg;
 
@@ -729,7 +727,6 @@ static DEFINE_MUTEX(cf_diag_ctrset_mutex);
 static struct cf_diag_ctrset {
 	unsigned long ctrset;		/* Bit mask of counter set to read */
 	cpumask_t mask;			/* CPU mask to read from */
-	time64_t lastread;		/* Epoch counter set last read */
 } cf_diag_ctrset;
 
 static void cf_diag_ctrset_clear(void)
@@ -866,27 +863,16 @@ static int cf_diag_all_read(unsigned long arg)
 {
 	struct cf_diag_call_on_cpu_parm p;
 	cpumask_var_t mask;
-	time64_t now;
+	int rc;
-	int rc = 0;
 
 	debug_sprintf_event(cf_diag_dbg, 5, "%s\n", __func__);
 	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
-	now = ktime_get_seconds();
+
-	if (cf_diag_ctrset.lastread + cf_diag_interval > now) {
-		debug_sprintf_event(cf_diag_dbg, 5, "%s now %lld "
-				    " lastread %lld\n", __func__, now,
-				    cf_diag_ctrset.lastread);
-		rc = -EAGAIN;
-		goto out;
-	} else {
-		cf_diag_ctrset.lastread = now;
-	}
 	p.sets = cf_diag_ctrset.ctrset;
 	cpumask_and(mask, &cf_diag_ctrset.mask, cpu_online_mask);
 	on_each_cpu_mask(mask, cf_diag_cpu_read, &p, 1);
 	rc = cf_diag_all_copy(arg, mask);
-out:
 	free_cpumask_var(mask);
 	debug_sprintf_event(cf_diag_dbg, 5, "%s rc %d\n", __func__, rc);
 	return rc;

arch/s390/kernel/time.c

@@ -68,10 +68,10 @@ EXPORT_SYMBOL(s390_epoch_delta_notifier);
 
 unsigned char ptff_function_mask[16];
 
-static unsigned long long lpar_offset;
+static unsigned long lpar_offset;
-static unsigned long long initial_leap_seconds;
+static unsigned long initial_leap_seconds;
-static unsigned long long tod_steering_end;
+static unsigned long tod_steering_end;
-static long long tod_steering_delta;
+static long tod_steering_delta;
 
 /*
  * Get time offsets with PTFF
@@ -96,7 +96,7 @@ void __init time_early_init(void)
 
 	/* get initial leap seconds */
 	if (ptff_query(PTFF_QUI) && ptff(&qui, sizeof(qui), PTFF_QUI) == 0)
-		initial_leap_seconds = (unsigned long long)
+		initial_leap_seconds = (unsigned long)
 			((long) qui.old_leap * 4096000000L);
 }
 
@@ -222,7 +222,7 @@ void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
 
 static u64 read_tod_clock(struct clocksource *cs)
 {
-	unsigned long long now, adj;
+	unsigned long now, adj;
 
 	preempt_disable(); /* protect from changes to steering parameters */
 	now = get_tod_clock();
@@ -362,7 +362,7 @@ static inline int check_sync_clock(void)
  * Apply clock delta to the global data structures.
  * This is called once on the CPU that performed the clock sync.
  */
-static void clock_sync_global(unsigned long long delta)
+static void clock_sync_global(unsigned long delta)
 {
 	unsigned long now, adj;
 	struct ptff_qto qto;
@@ -378,7 +378,7 @@ static void clock_sync_global(unsigned long long delta)
 			-(adj >> 15) : (adj >> 15);
 	tod_steering_delta += delta;
 	if ((abs(tod_steering_delta) >> 48) != 0)
-		panic("TOD clock sync offset %lli is too large to drift\n",
+		panic("TOD clock sync offset %li is too large to drift\n",
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
 	vdso_data->arch_data.tod_steering_end = tod_steering_end;
@@ -394,7 +394,7 @@ static void clock_sync_global(unsigned long long delta)
  * Apply clock delta to the per-CPU data structures of this CPU.
  * This is called for each online CPU after the call to clock_sync_global.
  */
-static void clock_sync_local(unsigned long long delta)
+static void clock_sync_local(unsigned long delta)
 {
 	/* Add the delta to the clock comparator. */
 	if (S390_lowcore.clock_comparator != clock_comparator_max) {
@@ -418,7 +418,7 @@ static void __init time_init_wq(void)
 struct clock_sync_data {
 	atomic_t cpus;
 	int in_sync;
-	unsigned long long clock_delta;
+	unsigned long clock_delta;
 };
 
 /*
@@ -538,7 +538,7 @@ static int stpinfo_valid(void)
 static int stp_sync_clock(void *data)
 {
 	struct clock_sync_data *sync = data;
-	unsigned long long clock_delta, flags;
+	u64 clock_delta, flags;
 	static int first;
 	int rc;
 
@@ -720,8 +720,8 @@ static ssize_t ctn_id_show(struct device *dev,
 
 	mutex_lock(&stp_mutex);
 	if (stpinfo_valid())
-		ret = sprintf(buf, "%016llx\n",
+		ret = sprintf(buf, "%016lx\n",
-			      *(unsigned long long *) stp_info.ctnid);
+			      *(unsigned long *) stp_info.ctnid);
 	mutex_unlock(&stp_mutex);
 	return ret;
 }
@@ -794,7 +794,7 @@ static ssize_t leap_seconds_scheduled_show(struct device *dev,
 	if (!stzi.lsoib.p)
 		return sprintf(buf, "0,0\n");
 
-	return sprintf(buf, "%llu,%d\n",
+	return sprintf(buf, "%lu,%d\n",
 		       tod_to_ns(stzi.lsoib.nlsout - TOD_UNIX_EPOCH) / NSEC_PER_SEC,
 		       stzi.lsoib.nlso - stzi.lsoib.also);
 }

arch/s390/kernel/topology.c

@@ -76,8 +76,6 @@ static void cpu_group_map(cpumask_t *dst, struct mask_info *info, unsigned int c
 			}
 			info = info->next;
 		}
-		if (cpumask_empty(&mask))
-			cpumask_copy(&mask, cpumask_of(cpu));
 		break;
 	case TOPOLOGY_MODE_PACKAGE:
 		cpumask_copy(&mask, cpu_present_mask);

arch/s390/kvm/interrupt.c

@@ -1287,7 +1287,7 @@ static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
 			/* already expired? */
 			if (cputm >> 63)
 				return 0;
-			return min(sltime, tod_to_ns(cputm));
+			return min_t(u64, sltime, tod_to_ns(cputm));
 		}
 	} else if (cpu_timer_interrupts_enabled(vcpu)) {
 		sltime = kvm_s390_get_cpu_timer(vcpu);

arch/sparc/configs/sparc64_defconfig

@@ -93,7 +93,7 @@ CONFIG_NETDEVICES=y
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=m
 CONFIG_SUNLANCE=m
-CONFIG_HAPPYMEAL=m
+CONFIG_HAPPYMEAL=y
 CONFIG_SUNGEM=m
 CONFIG_SUNVNET=m
 CONFIG_LDMVSW=m
@@ -234,9 +234,7 @@ CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRC16=m
 CONFIG_LIBCRC32C=m
 CONFIG_VCC=m
-CONFIG_ATA=y
 CONFIG_PATA_CMD64X=y
-CONFIG_HAPPYMEAL=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_DEVTMPFS=y

arch/sparc/include/asm/elf_64.h

@@ -8,7 +8,6 @@
 
 #include <asm/ptrace.h>
 #include <asm/processor.h>
-#include <asm/extable_64.h>
 #include <asm/spitfire.h>
 #include <asm/adi.h>
 

arch/sparc/include/asm/extable.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_EXTABLE64_H
+#ifndef __ASM_EXTABLE_H
-#define __ASM_EXTABLE64_H
+#define __ASM_EXTABLE_H
 /*
  * The exception table consists of pairs of addresses: the first is the
  * address of an instruction that is allowed to fault, and the second is

arch/sparc/include/asm/processor_32.h

@@ -50,16 +50,12 @@ struct thread_struct {
 	unsigned long   fsr;
 	unsigned long   fpqdepth;
 	struct fpq	fpqueue[16];
-	unsigned long flags;
 	mm_segment_t current_ds;
 };
 
-#define SPARC_FLAG_KTHREAD      0x1    /* task is a kernel thread */
-#define SPARC_FLAG_UNALIGNED    0x2    /* is allowed to do unaligned accesses */
-
 #define INIT_THREAD  { \
-	.flags = SPARC_FLAG_KTHREAD, \
 	.current_ds = KERNEL_DS, \
+	.kregs = (struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
 }
 
 /* Do necessary setup to start up a newly executed thread. */

arch/sparc/include/asm/thread_info_64.h

@@ -118,6 +118,7 @@ struct thread_info {
 	.task		=	&tsk,			\
 	.current_ds	=	ASI_P,			\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
+	.kregs		=	(struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
 }
 
 /* how to get the thread information struct from C */

arch/sparc/include/asm/uaccess.h

@@ -1,6 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ___ASM_SPARC_UACCESS_H
 #define ___ASM_SPARC_UACCESS_H
+
+#include <asm/extable.h>
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/uaccess_64.h>
 #else

arch/sparc/include/asm/uaccess_32.h

@@ -13,9 +13,6 @@
 
 #include <asm/processor.h>
 
-#define ARCH_HAS_SORT_EXTABLE
-#define ARCH_HAS_SEARCH_EXTABLE
-
 /* Sparc is not segmented, however we need to be able to fool access_ok()
  * when doing system calls from kernel mode legitimately.
  *
@@ -40,36 +37,6 @@
 #define __access_ok(addr, size) (__user_ok((addr) & get_fs().seg, (size)))
 #define access_ok(addr, size) __access_ok((unsigned long)(addr), size)
 
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- *
- * There is a special way how to put a range of potentially faulting
- * insns (like twenty ldd/std's with now intervening other instructions)
- * You specify address of first in insn and 0 in fixup and in the next
- * exception_table_entry you specify last potentially faulting insn + 1
- * and in fixup the routine which should handle the fault.
- * That fixup code will get
- * (faulting_insn_address - first_insn_in_the_range_address)/4
- * in %g2 (ie. index of the faulting instruction in the range).
- */
-
-struct exception_table_entry
-{
-        unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise.  */
-unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
-
 /* Uh, these should become the main single-value transfer routines..
  * They automatically use the right size if we just have the right
  * pointer type..
@@ -252,12 +219,7 @@ static inline unsigned long __clear_user(void __user *addr, unsigned long size)
 	unsigned long ret;
 
 	__asm__ __volatile__ (
-		".section __ex_table,#alloc\n\t"
-		".align 4\n\t"
-		".word 1f,3\n\t"
-		".previous\n\t"
 		"mov %2, %%o1\n"
-		"1:\n\t"
 		"call __bzero\n\t"
 		" mov %1, %%o0\n\t"
 		"mov %%o0, %0\n"

arch/sparc/include/asm/uaccess_64.h

@@ -10,7 +10,6 @@
 #include <linux/string.h>
 #include <asm/asi.h>
 #include <asm/spitfire.h>
-#include <asm/extable_64.h>
 
 #include <asm/processor.h>
 

arch/sparc/kernel/head_32.S

@@ -515,7 +515,7 @@ continue_boot:
 
 		/* I want a kernel stack NOW! */
 		set	init_thread_union, %g1
-		set	(THREAD_SIZE - STACKFRAME_SZ), %g2
+		set	(THREAD_SIZE - STACKFRAME_SZ - TRACEREG_SZ), %g2
 		add	%g1, %g2, %sp
 		mov	0, %fp			/* And for good luck */
 

arch/sparc/kernel/head_64.S

@@ -706,7 +706,7 @@ tlb_fixup_done:
 	wr	%g0, ASI_P, %asi
 	mov	1, %g1
 	sllx	%g1, THREAD_SHIFT, %g1
-	sub	%g1, (STACKFRAME_SZ + STACK_BIAS), %g1
+	sub	%g1, (STACKFRAME_SZ + STACK_BIAS + TRACEREG_SZ), %g1
 	add	%g6, %g1, %sp
 
 	/* Set per-cpu pointer initially to zero, this makes

arch/sparc/kernel/process_32.c

@@ -216,16 +216,6 @@ void flush_thread(void)
 		clear_thread_flag(TIF_USEDFPU);
 #endif
 	}
-
-	/* This task is no longer a kernel thread. */
-	if (current->thread.flags & SPARC_FLAG_KTHREAD) {
-		current->thread.flags &= ~SPARC_FLAG_KTHREAD;
-
-		/* We must fixup kregs as well. */
-		/* XXX This was not fixed for ti for a while, worked. Unused? */
-		current->thread.kregs = (struct pt_regs *)
-		    (task_stack_page(current) + (THREAD_SIZE - TRACEREG_SZ));
-	}
 }
 
 static inline struct sparc_stackf __user *
@@ -313,7 +303,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 		extern int nwindows;
 		unsigned long psr;
 		memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ);
-		p->thread.flags |= SPARC_FLAG_KTHREAD;
 		p->thread.current_ds = KERNEL_DS;
 		ti->kpc = (((unsigned long) ret_from_kernel_thread) - 0x8);
 		childregs->u_regs[UREG_G1] = sp; /* function */
@@ -325,7 +314,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	}
 	memcpy(new_stack, (char *)regs - STACKFRAME_SZ, STACKFRAME_SZ + TRACEREG_SZ);
 	childregs->u_regs[UREG_FP] = sp;
-	p->thread.flags &= ~SPARC_FLAG_KTHREAD;
 	p->thread.current_ds = USER_DS;
 	ti->kpc = (((unsigned long) ret_from_fork) - 0x8);
 	ti->kpsr = current->thread.fork_kpsr | PSR_PIL;

arch/sparc/kernel/setup_32.c

@@ -266,7 +266,6 @@ static __init void leon_patch(void)
 }
 
 struct tt_entry *sparc_ttable;
-static struct pt_regs fake_swapper_regs;
 
 /* Called from head_32.S - before we have setup anything
  * in the kernel. Be very careful with what you do here.
@@ -363,8 +362,6 @@ void __init setup_arch(char **cmdline_p)
 		(*(linux_dbvec->teach_debugger))();
 	}
 
-	init_task.thread.kregs = &fake_swapper_regs;
-
 	/* Run-time patch instructions to match the cpu model */
 	per_cpu_patch();
 

arch/sparc/kernel/setup_64.c

@@ -165,8 +165,6 @@ extern int root_mountflags;
 
 char reboot_command[COMMAND_LINE_SIZE];
 
-static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 };
-
 static void __init per_cpu_patch(void)
 {
 	struct cpuid_patch_entry *p;
@@ -661,8 +659,6 @@ void __init setup_arch(char **cmdline_p)
 	rd_image_start = ram_flags & RAMDISK_IMAGE_START_MASK;
 #endif
 
-	task_thread_info(&init_task)->kregs = &fake_swapper_regs;
-
 #ifdef CONFIG_IP_PNP
 	if (!ic_set_manually) {
 		phandle chosen = prom_finddevice("/chosen");

arch/sparc/kernel/traps_64.c

@@ -275,14 +275,13 @@ bool is_no_fault_exception(struct pt_regs *regs)
 			asi = (regs->tstate >> 24); /* saved %asi       */
 		else
 			asi = (insn >> 5);	    /* immediate asi    */
-		if ((asi & 0xf2) == ASI_PNF) {
+		if ((asi & 0xf6) == ASI_PNF) {
-			if (insn & 0x1000000) {     /* op3[5:4]=3       */
+			if (insn & 0x200000)        /* op3[2], stores   */
-				handle_ldf_stq(insn, regs);
-				return true;
-			} else if (insn & 0x200000) { /* op3[2], stores */
 				return false;
-			}
+			if (insn & 0x1000000)       /* op3[5:4]=3 (fp)  */
-			handle_ld_nf(insn, regs);
+				handle_ldf_stq(insn, regs);
+			else
+				handle_ld_nf(insn, regs);
 			return true;
 		}
 	}

arch/sparc/kernel/unaligned_32.c

@@ -16,6 +16,7 @@
 #include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <linux/perf_event.h>
+#include <linux/extable.h>
 
 #include <asm/setup.h>
 
@@ -213,10 +214,10 @@ static inline int ok_for_kernel(unsigned int insn)
 
 static void kernel_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
 {
-	unsigned long g2 = regs->u_regs [UREG_G2];
+	const struct exception_table_entry *entry;
-	unsigned long fixup = search_extables_range(regs->pc, &g2);
 
-	if (!fixup) {
+	entry = search_exception_tables(regs->pc);
+	if (!entry) {
 		unsigned long address = compute_effective_address(regs, insn);
         	if(address < PAGE_SIZE) {
                 	printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference in mna handler");
@@ -232,9 +233,8 @@ static void kernel_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
 	        die_if_kernel("Oops", regs);
 		/* Not reached */
 	}
-	regs->pc = fixup;
+	regs->pc = entry->fixup;
 	regs->npc = regs->pc + 4;
-	regs->u_regs [UREG_G2] = g2;
 }
 
 asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
@@ -274,103 +274,9 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 	}
 }
 
-static inline int ok_for_user(struct pt_regs *regs, unsigned int insn,
+asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
-			      enum direction dir)
-{
-	unsigned int reg;
-	int size = ((insn >> 19) & 3) == 3 ? 8 : 4;
-
-	if ((regs->pc | regs->npc) & 3)
-		return 0;
-
-	/* Must access_ok() in all the necessary places. */
-#define WINREG_ADDR(regnum) \
-	((void __user *)(((unsigned long *)regs->u_regs[UREG_FP])+(regnum)))
-
-	reg = (insn >> 25) & 0x1f;
-	if (reg >= 16) {
-		if (!access_ok(WINREG_ADDR(reg - 16), size))
-			return -EFAULT;
-	}
-	reg = (insn >> 14) & 0x1f;
-	if (reg >= 16) {
-		if (!access_ok(WINREG_ADDR(reg - 16), size))
-			return -EFAULT;
-	}
-	if (!(insn & 0x2000)) {
-		reg = (insn & 0x1f);
-		if (reg >= 16) {
-			if (!access_ok(WINREG_ADDR(reg - 16), size))
-				return -EFAULT;
-		}
-	}
-#undef WINREG_ADDR
-	return 0;
-}
-
-static void user_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
 {
 	send_sig_fault(SIGBUS, BUS_ADRALN,
 		       (void __user *)safe_compute_effective_address(regs, insn),
 		       0, current);
 }
-
-asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
-{
-	enum direction dir;
-
-	if(!(current->thread.flags & SPARC_FLAG_UNALIGNED) ||
-	   (((insn >> 30) & 3) != 3))
-		goto kill_user;
-	dir = decode_direction(insn);
-	if(!ok_for_user(regs, insn, dir)) {
-		goto kill_user;
-	} else {
-		int err, size = decode_access_size(insn);
-		unsigned long addr;
-
-		if(floating_point_load_or_store_p(insn)) {
-			printk("User FPU load/store unaligned unsupported.\n");
-			goto kill_user;
-		}
-
-		addr = compute_effective_address(regs, insn);
-		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
-		switch(dir) {
-		case load:
-			err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f),
-							 regs),
-					  size, (unsigned long *) addr,
-					  decode_signedness(insn));
-			break;
-
-		case store:
-			err = do_int_store(((insn>>25)&0x1f), size,
-					   (unsigned long *) addr, regs);
-			break;
-
-		case both:
-			/*
-			 * This was supported in 2.4. However, we question
-			 * the value of SWAP instruction across word boundaries.
-			 */
-			printk("Unaligned SWAP unsupported.\n");
-			err = -EFAULT;
-			break;
-
-		default:
-			unaligned_panic("Impossible user unaligned trap.");
-			goto out;
-		}
-		if (err)
-			goto kill_user;
-		else
-			advance(regs);
-		goto out;
-	}
-
-kill_user:
-	user_mna_trap_fault(regs, insn);
-out:
-	;
-}

arch/sparc/lib/checksum_32.S

@@ -155,13 +155,6 @@ cpout:	retl						! get outta here
         .text;                                  \
         .align  4
 
-#define EXT(start,end)				\
-        .section __ex_table,ALLOC;		\
-        .align  4;                              \
-        .word   start, 0, end, cc_fault;         \
-        .text;                                  \
-        .align  4
-
 	/* This aligned version executes typically in 8.5 superscalar cycles, this
 	 * is the best I can do.  I say 8.5 because the final add will pair with
 	 * the next ldd in the main unrolled loop.  Thus the pipe is always full.
@@ -169,20 +162,20 @@ cpout:	retl						! get outta here
 	 * please check the fixup code below as well.
 	 */
 #define CSUMCOPY_BIGCHUNK_ALIGNED(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7)	\
-	ldd	[src + off + 0x00], t0;							\
+	EX(ldd	[src + off + 0x00], t0);						\
-	ldd	[src + off + 0x08], t2;							\
+	EX(ldd	[src + off + 0x08], t2);						\
 	addxcc	t0, sum, sum;								\
-	ldd	[src + off + 0x10], t4;							\
+	EX(ldd	[src + off + 0x10], t4);						\
 	addxcc	t1, sum, sum;								\
-	ldd	[src + off + 0x18], t6;							\
+	EX(ldd	[src + off + 0x18], t6);						\
 	addxcc	t2, sum, sum;								\
-	std	t0, [dst + off + 0x00];							\
+	EX(std	t0, [dst + off + 0x00]);						\
 	addxcc	t3, sum, sum;								\
-	std	t2, [dst + off + 0x08];							\
+	EX(std	t2, [dst + off + 0x08]);						\
 	addxcc	t4, sum, sum;								\
-	std	t4, [dst + off + 0x10];							\
+	EX(std	t4, [dst + off + 0x10]);						\
 	addxcc	t5, sum, sum;								\
-	std	t6, [dst + off + 0x18];							\
+	EX(std	t6, [dst + off + 0x18]);						\
 	addxcc	t6, sum, sum;								\
 	addxcc	t7, sum, sum;
 
@@ -191,39 +184,39 @@ cpout:	retl						! get outta here
 	 * Viking MXCC into streaming mode.  Ho hum...
 	 */
 #define CSUMCOPY_BIGCHUNK(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7)	\
-	ldd	[src + off + 0x00], t0;						\
+	EX(ldd	[src + off + 0x00], t0);					\
-	ldd	[src + off + 0x08], t2;						\
+	EX(ldd	[src + off + 0x08], t2);					\
-	ldd	[src + off + 0x10], t4;						\
+	EX(ldd	[src + off + 0x10], t4);					\
-	ldd	[src + off + 0x18], t6;						\
+	EX(ldd	[src + off + 0x18], t6);					\
-	st	t0, [dst + off + 0x00];						\
+	EX(st	t0, [dst + off + 0x00]);					\
 	addxcc	t0, sum, sum;							\
-	st	t1, [dst + off + 0x04];						\
+	EX(st	t1, [dst + off + 0x04]);					\
 	addxcc	t1, sum, sum;							\
-	st	t2, [dst + off + 0x08];						\
+	EX(st	t2, [dst + off + 0x08]);					\
 	addxcc	t2, sum, sum;							\
-	st	t3, [dst + off + 0x0c];						\
+	EX(st	t3, [dst + off + 0x0c]);					\
 	addxcc	t3, sum, sum;							\
-	st	t4, [dst + off + 0x10];						\
+	EX(st	t4, [dst + off + 0x10]);					\
 	addxcc	t4, sum, sum;							\
-	st	t5, [dst + off + 0x14];						\
+	EX(st	t5, [dst + off + 0x14]);					\
 	addxcc	t5, sum, sum;							\
-	st	t6, [dst + off + 0x18];						\
+	EX(st	t6, [dst + off + 0x18]);					\
 	addxcc	t6, sum, sum;							\
-	st	t7, [dst + off + 0x1c];						\
+	EX(st	t7, [dst + off + 0x1c]);					\
 	addxcc	t7, sum, sum;
 
 	/* Yuck, 6 superscalar cycles... */
 #define CSUMCOPY_LASTCHUNK(src, dst, sum, off, t0, t1, t2, t3)	\
-	ldd	[src - off - 0x08], t0;				\
+	EX(ldd	[src - off - 0x08], t0);			\
-	ldd	[src - off - 0x00], t2;				\
+	EX(ldd	[src - off - 0x00], t2);			\
 	addxcc	t0, sum, sum;					\
-	st	t0, [dst - off - 0x08];				\
+	EX(st	t0, [dst - off - 0x08]);			\
 	addxcc	t1, sum, sum;					\
-	st	t1, [dst - off - 0x04];				\
+	EX(st	t1, [dst - off - 0x04]);			\
 	addxcc	t2, sum, sum;					\
-	st	t2, [dst - off - 0x00];				\
+	EX(st	t2, [dst - off - 0x00]);			\
 	addxcc	t3, sum, sum;					\
-	st	t3, [dst - off + 0x04];
+	EX(st	t3, [dst - off + 0x04]);
 
 	/* Handle the end cruft code out of band for better cache patterns. */
 cc_end_cruft:
@@ -331,7 +324,6 @@ __csum_partial_copy_sparc_generic:
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-10:	EXT(5b, 10b)			! note for exception handling
 	sub	%g1, 128, %g1		! detract from length
 	addx	%g0, %g7, %g7		! add in last carry bit
 	andcc	%g1, 0xffffff80, %g0	! more to csum?
@@ -356,8 +348,7 @@ cctbl:	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x68,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x28,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x18,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x08,%g2,%g3,%g4,%g5)
-12:	EXT(cctbl, 12b)			! note for exception table handling
+12:	addx	%g0, %g7, %g7
-	addx	%g0, %g7, %g7
 	andcc	%o3, 0xf, %g0		! check for low bits set
 ccte:	bne	cc_end_cruft		! something left, handle it out of band
 	 andcc	%o3, 8, %g0		! begin checks for that code
@@ -367,7 +358,6 @@ ccdbl:	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x00,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-11:	EXT(ccdbl, 11b)			! note for exception table handling
 	sub	%g1, 128, %g1		! detract from length
 	addx	%g0, %g7, %g7		! add in last carry bit
 	andcc	%g1, 0xffffff80, %g0	! more to csum?

arch/sparc/lib/copy_user.S

@@ -21,98 +21,134 @@
 /* Work around cpp -rob */
 #define ALLOC #alloc
 #define EXECINSTR #execinstr
+
+#define EX_ENTRY(l1, l2)			\
+	.section __ex_table,ALLOC;		\
+	.align	4;				\
+	.word	l1, l2;				\
+	.text;
+
 #define EX(x,y,a,b) 				\
 98: 	x,y;					\
 	.section .fixup,ALLOC,EXECINSTR;	\
 	.align	4;				\
-99:	ba fixupretl;				\
+99:	retl;					\
-	 a, b, %g3;				\
+	 a, b, %o0;				\
-	.section __ex_table,ALLOC;		\
+	EX_ENTRY(98b, 99b)
-	.align	4;				\
-	.word	98b, 99b;			\
-	.text;					\
-	.align	4
 
 #define EX2(x,y,c,d,e,a,b) 			\
 98: 	x,y;					\
 	.section .fixup,ALLOC,EXECINSTR;	\
 	.align	4;				\
 99:	c, d, e;				\
-	ba fixupretl;				\
+	retl;					\
-	 a, b, %g3;				\
+	 a, b, %o0;				\
-	.section __ex_table,ALLOC;		\
+	EX_ENTRY(98b, 99b)
-	.align	4;				\
-	.word	98b, 99b;			\
-	.text;					\
-	.align	4
 
 #define EXO2(x,y) 				\
 98: 	x, y;					\
-	.section __ex_table,ALLOC;		\
+	EX_ENTRY(98b, 97f)
-	.align	4;				\
-	.word	98b, 97f;			\
-	.text;					\
-	.align	4
 
-#define EXT(start,end,handler)			\
+#define LD(insn, src, offset, reg, label)	\
-	.section __ex_table,ALLOC;		\
+98:	insn [%src + (offset)], %reg;		\
-	.align	4;				\
+	.section .fixup,ALLOC,EXECINSTR;	\
-	.word	start, 0, end, handler;		\
+99:	ba	label;				\
-	.text;					\
+	 mov	offset, %g5;			\
-	.align	4
+	EX_ENTRY(98b, 99b)
 
-/* Please do not change following macros unless you change logic used
+#define ST(insn, dst, offset, reg, label)	\
- * in .fixup at the end of this file as well
+98:	insn %reg, [%dst + (offset)];		\
- */
+	.section .fixup,ALLOC,EXECINSTR;	\
+99:	ba	label;				\
+	 mov	offset, %g5;			\
+	EX_ENTRY(98b, 99b)
 
 /* Both these macros have to start with exactly the same insn */
+/* left: g7 + (g1 % 128) - offset */
 #define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
-	ldd	[%src + (offset) + 0x00], %t0; \
+	LD(ldd, src, offset + 0x00, t0, bigchunk_fault)	\
-	ldd	[%src + (offset) + 0x08], %t2; \
+	LD(ldd, src, offset + 0x08, t2, bigchunk_fault)	\
-	ldd	[%src + (offset) + 0x10], %t4; \
+	LD(ldd, src, offset + 0x10, t4, bigchunk_fault)	\
-	ldd	[%src + (offset) + 0x18], %t6; \
+	LD(ldd, src, offset + 0x18, t6, bigchunk_fault)	\
-	st	%t0, [%dst + (offset) + 0x00]; \
+	ST(st, dst, offset + 0x00, t0, bigchunk_fault)	\
-	st	%t1, [%dst + (offset) + 0x04]; \
+	ST(st, dst, offset + 0x04, t1, bigchunk_fault)	\
-	st	%t2, [%dst + (offset) + 0x08]; \
+	ST(st, dst, offset + 0x08, t2, bigchunk_fault)	\
-	st	%t3, [%dst + (offset) + 0x0c]; \
+	ST(st, dst, offset + 0x0c, t3, bigchunk_fault)	\
-	st	%t4, [%dst + (offset) + 0x10]; \
+	ST(st, dst, offset + 0x10, t4, bigchunk_fault)	\
-	st	%t5, [%dst + (offset) + 0x14]; \
+	ST(st, dst, offset + 0x14, t5, bigchunk_fault)	\
-	st	%t6, [%dst + (offset) + 0x18]; \
+	ST(st, dst, offset + 0x18, t6, bigchunk_fault)	\
-	st	%t7, [%dst + (offset) + 0x1c];
+	ST(st, dst, offset + 0x1c, t7, bigchunk_fault)
 
+/* left: g7 + (g1 % 128) - offset */
 #define MOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
-	ldd	[%src + (offset) + 0x00], %t0; \
+	LD(ldd, src, offset + 0x00, t0, bigchunk_fault)	\
-	ldd	[%src + (offset) + 0x08], %t2; \
+	LD(ldd, src, offset + 0x08, t2, bigchunk_fault)	\
-	ldd	[%src + (offset) + 0x10], %t4; \
+	LD(ldd, src, offset + 0x10, t4, bigchunk_fault)	\
-	ldd	[%src + (offset) + 0x18], %t6; \
+	LD(ldd, src, offset + 0x18, t6, bigchunk_fault)	\
-	std	%t0, [%dst + (offset) + 0x00]; \
+	ST(std, dst, offset + 0x00, t0, bigchunk_fault)	\
-	std	%t2, [%dst + (offset) + 0x08]; \
+	ST(std, dst, offset + 0x08, t2, bigchunk_fault)	\
-	std	%t4, [%dst + (offset) + 0x10]; \
+	ST(std, dst, offset + 0x10, t4, bigchunk_fault)	\
-	std	%t6, [%dst + (offset) + 0x18];
+	ST(std, dst, offset + 0x18, t6, bigchunk_fault)
 
+	.section .fixup,#alloc,#execinstr
+bigchunk_fault:
+	sub	%g7, %g5, %o0
+	and	%g1, 127, %g1
+	retl
+	 add	%o0, %g1, %o0
+
+/* left: offset + 16 + (g1 % 16) */
 #define MOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
-	ldd	[%src - (offset) - 0x10], %t0; \
+	LD(ldd, src, -(offset + 0x10), t0, lastchunk_fault)	\
-	ldd	[%src - (offset) - 0x08], %t2; \
+	LD(ldd, src, -(offset + 0x08), t2, lastchunk_fault)	\
-	st	%t0, [%dst - (offset) - 0x10]; \
+	ST(st, dst, -(offset + 0x10), t0, lastchunk_fault)	\
-	st	%t1, [%dst - (offset) - 0x0c]; \
+	ST(st, dst, -(offset + 0x0c), t1, lastchunk_fault)	\
-	st	%t2, [%dst - (offset) - 0x08]; \
+	ST(st, dst, -(offset + 0x08), t2, lastchunk_fault)	\
-	st	%t3, [%dst - (offset) - 0x04];
+	ST(st, dst, -(offset + 0x04), t3, lastchunk_fault)
 
+	.section .fixup,#alloc,#execinstr
+lastchunk_fault:
+	and	%g1, 15, %g1
+	retl
+	 sub	%g1, %g5, %o0
+
+/* left: o3 + (o2 % 16) - offset */
 #define MOVE_HALFCHUNK(src, dst, offset, t0, t1, t2, t3) \
-	lduh	[%src + (offset) + 0x00], %t0; \
+	LD(lduh, src, offset + 0x00, t0, halfchunk_fault)	\
-	lduh	[%src + (offset) + 0x02], %t1; \
+	LD(lduh, src, offset + 0x02, t1, halfchunk_fault)	\
-	lduh	[%src + (offset) + 0x04], %t2; \
+	LD(lduh, src, offset + 0x04, t2, halfchunk_fault)	\
-	lduh	[%src + (offset) + 0x06], %t3; \
+	LD(lduh, src, offset + 0x06, t3, halfchunk_fault)	\
-	sth	%t0, [%dst + (offset) + 0x00]; \
+	ST(sth, dst, offset + 0x00, t0, halfchunk_fault)	\
-	sth	%t1, [%dst + (offset) + 0x02]; \
+	ST(sth, dst, offset + 0x02, t1, halfchunk_fault)	\
-	sth	%t2, [%dst + (offset) + 0x04]; \
+	ST(sth, dst, offset + 0x04, t2, halfchunk_fault)	\
-	sth	%t3, [%dst + (offset) + 0x06];
+	ST(sth, dst, offset + 0x06, t3, halfchunk_fault)
 
+/* left: o3 + (o2 % 16) + offset + 2 */
 #define MOVE_SHORTCHUNK(src, dst, offset, t0, t1) \
-	ldub	[%src - (offset) - 0x02], %t0; \
+	LD(ldub, src, -(offset + 0x02), t0, halfchunk_fault)	\
-	ldub	[%src - (offset) - 0x01], %t1; \
+	LD(ldub, src, -(offset + 0x01), t1, halfchunk_fault)	\
-	stb	%t0, [%dst - (offset) - 0x02]; \
+	ST(stb, dst, -(offset + 0x02), t0, halfchunk_fault)	\
-	stb	%t1, [%dst - (offset) - 0x01];
+	ST(stb, dst, -(offset + 0x01), t1, halfchunk_fault)
+
+	.section .fixup,#alloc,#execinstr
+halfchunk_fault:
+	and	%o2, 15, %o2
+	sub	%o3, %g5, %o3
+	retl
+	 add	%o2, %o3, %o0
+
+/* left: offset + 2 + (o2 % 2) */
+#define MOVE_LAST_SHORTCHUNK(src, dst, offset, t0, t1) \
+	LD(ldub, src, -(offset + 0x02), t0, last_shortchunk_fault)	\
+	LD(ldub, src, -(offset + 0x01), t1, last_shortchunk_fault)	\
+	ST(stb, dst, -(offset + 0x02), t0, last_shortchunk_fault)	\
+	ST(stb, dst, -(offset + 0x01), t1, last_shortchunk_fault)
+
+	.section .fixup,#alloc,#execinstr
+last_shortchunk_fault:
+	and	%o2, 1, %o2
+	retl
+	 sub	%o2, %g5, %o0
 
 	.text
 	.align	4
@@ -182,8 +218,6 @@ __copy_user:	/* %o0=dst %o1=src %o2=len */
 	MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-80:
-	EXT(5b, 80b, 50f)
 	subcc	%g7, 128, %g7
 	add	%o1, 128, %o1
 	bne	5b
@@ -201,7 +235,6 @@ __copy_user:	/* %o0=dst %o1=src %o2=len */
 	jmpl	%o5 + %lo(copy_user_table_end), %g0
 	 add	%o0, %g7, %o0
 
-copy_user_table:
 	MOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
 	MOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
 	MOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
@@ -210,7 +243,6 @@ copy_user_table:
 	MOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
 	MOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
 copy_user_table_end:
-	EXT(copy_user_table, copy_user_table_end, 51f)
 	be	copy_user_last7
 	 andcc	%g1, 4, %g0
 
@@ -250,8 +282,6 @@ ldd_std:
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
 	MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-81:
-	EXT(ldd_std, 81b, 52f)
 	subcc	%g7, 128, %g7
 	add	%o1, 128, %o1
 	bne	ldd_std
@@ -290,8 +320,6 @@ cannot_optimize:
 10:
 	MOVE_HALFCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
 	MOVE_HALFCHUNK(o1, o0, 0x08, g2, g3, g4, g5)
-82:
-	EXT(10b, 82b, 53f)
 	subcc	%o3, 0x10, %o3
 	add	%o1, 0x10, %o1
 	bne	10b
@@ -308,8 +336,6 @@ byte_chunk:
 	MOVE_SHORTCHUNK(o1, o0, -0x0c, g2, g3)
 	MOVE_SHORTCHUNK(o1, o0, -0x0e, g2, g3)
 	MOVE_SHORTCHUNK(o1, o0, -0x10, g2, g3)
-83:
-	EXT(byte_chunk, 83b, 54f)
 	subcc	%o3, 0x10, %o3
 	add	%o1, 0x10, %o1
 	bne	byte_chunk
@@ -325,16 +351,14 @@ short_end:
 	add	%o1, %o3, %o1
 	jmpl	%o5 + %lo(short_table_end), %g0
 	 andcc	%o2, 1, %g0
-84:
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x08, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x06, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x04, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x02, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3)
+	MOVE_LAST_SHORTCHUNK(o1, o0, 0x00, g2, g3)
-	MOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3)
 short_table_end:
-	EXT(84b, short_table_end, 55f)
 	be	1f
 	 nop
 	EX(ldub	[%o1], %g2, add %g0, 1)
@@ -363,123 +387,8 @@ short_aligned_end:
 	.section .fixup,#alloc,#execinstr
 	.align	4
 97:
-	mov	%o2, %g3
-fixupretl:
 	retl
-	 mov	%g3, %o0
+	 mov	%o2, %o0
-
-/* exception routine sets %g2 to (broken_insn - first_insn)>>2 */
-50:
-/* This magic counts how many bytes are left when crash in MOVE_BIGCHUNK
- * happens. This is derived from the amount ldd reads, st stores, etc.
- * x = g2 % 12;
- * g3 = g1 + g7 - ((g2 / 12) * 32 + (x < 4) ? 0 : (x - 4) * 4);
- * o0 += (g2 / 12) * 32;
- */
-	cmp	%g2, 12
-	add	%o0, %g7, %o0
-	bcs	1f
-	 cmp	%g2, 24
-	bcs	2f
-	 cmp	%g2, 36
-	bcs	3f
-	 nop
-	sub	%g2, 12, %g2
-	sub	%g7, 32, %g7
-3:	sub	%g2, 12, %g2
-	sub	%g7, 32, %g7
-2:	sub	%g2, 12, %g2
-	sub	%g7, 32, %g7
-1:	cmp	%g2, 4
-	bcs,a	60f
-	 clr	%g2
-	sub	%g2, 4, %g2
-	sll	%g2, 2, %g2
-60:	and	%g1, 0x7f, %g3
-	sub	%o0, %g7, %o0
-	add	%g3, %g7, %g3
-	ba	fixupretl
-	 sub	%g3, %g2, %g3
-51:
-/* i = 41 - g2; j = i % 6;
- * g3 = (g1 & 15) + (i / 6) * 16 + (j < 4) ? (j + 1) * 4 : 16;
- * o0 -= (i / 6) * 16 + 16;
- */
-	neg	%g2
-	and	%g1, 0xf, %g1
-	add	%g2, 41, %g2
-	add	%o0, %g1, %o0
-1:	cmp	%g2, 6
-	bcs,a	2f
-	 cmp	%g2, 4
-	add	%g1, 16, %g1
-	b	1b
-	 sub	%g2, 6, %g2
-2:	bcc,a	2f
-	 mov	16, %g2
-	inc	%g2
-	sll	%g2, 2, %g2
-2:	add	%g1, %g2, %g3
-	ba	fixupretl
-	 sub	%o0, %g3, %o0
-52:
-/* g3 = g1 + g7 - (g2 / 8) * 32 + (g2 & 4) ? (g2 & 3) * 8 : 0;
-   o0 += (g2 / 8) * 32 */
-	andn	%g2, 7, %g4
-	add	%o0, %g7, %o0
-	andcc	%g2, 4, %g0
-	and	%g2, 3, %g2
-	sll	%g4, 2, %g4
-	sll	%g2, 3, %g2
-	bne	60b
-	 sub	%g7, %g4, %g7
-	ba	60b
-	 clr	%g2
-53:
-/* g3 = o3 + (o2 & 15) - (g2 & 8) - (g2 & 4) ? (g2 & 3) * 2 : 0;
-   o0 += (g2 & 8) */
-	and	%g2, 3, %g4
-	andcc	%g2, 4, %g0
-	and	%g2, 8, %g2
-	sll	%g4, 1, %g4
-	be	1f
-	 add	%o0, %g2, %o0
-	add	%g2, %g4, %g2
-1:	and	%o2, 0xf, %g3
-	add	%g3, %o3, %g3
-	ba	fixupretl
-	 sub	%g3, %g2, %g3
-54:
-/* g3 = o3 + (o2 & 15) - (g2 / 4) * 2 - (g2 & 2) ? (g2 & 1) : 0;
-   o0 += (g2 / 4) * 2 */
-	srl	%g2, 2, %o4
-	and	%g2, 1, %o5
-	srl	%g2, 1, %g2
-	add	%o4, %o4, %o4
-	and	%o5, %g2, %o5
-	and	%o2, 0xf, %o2
-	add	%o0, %o4, %o0
-	sub	%o3, %o5, %o3
-	sub	%o2, %o4, %o2
-	ba	fixupretl
-	 add	%o2, %o3, %g3
-55:
-/* i = 27 - g2;
-   g3 = (o2 & 1) + i / 4 * 2 + !(i & 3);
-   o0 -= i / 4 * 2 + 1 */
-	neg	%g2
-	and	%o2, 1, %o2
-	add	%g2, 27, %g2
-	srl	%g2, 2, %o5
-	andcc	%g2, 3, %g0
-	mov	1, %g2
-	add	%o5, %o5, %o5
-	be,a	1f
-	 clr	%g2
-1:	add	%g2, %o5, %g3
-	sub	%o0, %g3, %o0
-	ba	fixupretl
-	 add	%g3, %o2, %g3
 
 	.globl  __copy_user_end
 __copy_user_end:

arch/sparc/lib/memset.S

@@ -19,7 +19,7 @@
 98: 	x,y;					\
 	.section .fixup,ALLOC,EXECINSTR;	\
 	.align	4;				\
-99:	ba 30f;					\
+99:	retl;					\
 	 a, b, %o0;				\
 	.section __ex_table,ALLOC;		\
 	.align	4;				\
@@ -27,35 +27,44 @@
 	.text;					\
 	.align	4
 
-#define EXT(start,end,handler) 			\
+#define STORE(source, base, offset, n)		\
+98: 	std source, [base + offset + n];	\
+	.section .fixup,ALLOC,EXECINSTR;	\
+	.align	4;				\
+99:	ba 30f;					\
+	 sub %o3, n - offset, %o3;		\
 	.section __ex_table,ALLOC;		\
 	.align	4;				\
-	.word	start, 0, end, handler;		\
+	.word	98b, 99b;			\
 	.text;					\
-	.align	4
+	.align	4;
+
+#define STORE_LAST(source, base, offset, n)	\
+	EX(std source, [base - offset - n],	\
+	   add %o1, offset + n);
 
 /* Please don't change these macros, unless you change the logic
  * in the .fixup section below as well.
  * Store 64 bytes at (BASE + OFFSET) using value SOURCE. */
-#define ZERO_BIG_BLOCK(base, offset, source)    \
+#define ZERO_BIG_BLOCK(base, offset, source)	\
-	std	source, [base + offset + 0x00]; \
+	STORE(source, base, offset, 0x00);	\
-	std	source, [base + offset + 0x08]; \
+	STORE(source, base, offset, 0x08);	\
-	std	source, [base + offset + 0x10]; \
+	STORE(source, base, offset, 0x10);	\
-	std	source, [base + offset + 0x18]; \
+	STORE(source, base, offset, 0x18);	\
-	std	source, [base + offset + 0x20]; \
+	STORE(source, base, offset, 0x20);	\
-	std	source, [base + offset + 0x28]; \
+	STORE(source, base, offset, 0x28);	\
-	std	source, [base + offset + 0x30]; \
+	STORE(source, base, offset, 0x30);	\
-	std	source, [base + offset + 0x38];
+	STORE(source, base, offset, 0x38);
 
 #define ZERO_LAST_BLOCKS(base, offset, source)	\
-	std	source, [base - offset - 0x38]; \
+	STORE_LAST(source, base, offset, 0x38);	\
-	std	source, [base - offset - 0x30]; \
+	STORE_LAST(source, base, offset, 0x30); \
-	std	source, [base - offset - 0x28]; \
+	STORE_LAST(source, base, offset, 0x28);	\
-	std	source, [base - offset - 0x20]; \
+	STORE_LAST(source, base, offset, 0x20);	\
-	std	source, [base - offset - 0x18]; \
+	STORE_LAST(source, base, offset, 0x18);	\
-	std	source, [base - offset - 0x10]; \
+	STORE_LAST(source, base, offset, 0x10);	\
-	std	source, [base - offset - 0x08]; \
+	STORE_LAST(source, base, offset, 0x08);	\
-	std	source, [base - offset - 0x00];
+	STORE_LAST(source, base, offset, 0x00);
 
 	.text
 	.align 4
@@ -68,8 +77,6 @@ __bzero_begin:
 	.globl	memset
 	EXPORT_SYMBOL(__bzero)
 	EXPORT_SYMBOL(memset)
-	.globl	__memset_start, __memset_end
-__memset_start:
 memset:
 	mov	%o0, %g1
 	mov	1, %g4
@@ -122,8 +129,6 @@ __bzero:
 	ZERO_BIG_BLOCK(%o0, 0x00, %g2)
 	subcc	%o3, 128, %o3
 	ZERO_BIG_BLOCK(%o0, 0x40, %g2)
-11:
-	EXT(10b, 11b, 20f)
 	bne	10b
 	 add	%o0, 128, %o0
 
@@ -138,11 +143,9 @@ __bzero:
 	jmp	%o4
 	 add	%o0, %o2, %o0
 
-12:
 	ZERO_LAST_BLOCKS(%o0, 0x48, %g2)
 	ZERO_LAST_BLOCKS(%o0, 0x08, %g2)
 13:
-	EXT(12b, 13b, 21f)
 	be	8f
 	 andcc	%o1, 4, %g0
 
@@ -182,37 +185,13 @@ __bzero:
 5:
 	retl
 	 clr	%o0
-__memset_end:
 
 	.section .fixup,#alloc,#execinstr
 	.align	4
-20:
-	cmp	%g2, 8
-	bleu	1f
-	 and	%o1, 0x7f, %o1
-	sub	%g2, 9, %g2
-	add	%o3, 64, %o3
-1:
-	sll	%g2, 3, %g2
-	add	%o3, %o1, %o0
-	b 30f
-	 sub	%o0, %g2, %o0
-21:
-	mov	8, %o0
-	and	%o1, 7, %o1
-	sub	%o0, %g2, %o0
-	sll	%o0, 3, %o0
-	b 30f
-	 add	%o0, %o1, %o0
 30:
-/* %o4 is faulting address, %o5 is %pc where fault occurred */
+	and	%o1, 0x7f, %o1
-	save	%sp, -104, %sp
+	retl
-	mov	%i5, %o0
+	 add	%o3, %o1, %o0
-	mov	%i7, %o1
-	call	lookup_fault
-	 mov	%i4, %o2
-	ret
-	 restore
 
 	.globl __bzero_end
 __bzero_end: