9 files changed, 36 insertions, 121 deletions

diff --git a/arch/sparc/kernel/iommu-common.c b/arch/sparc/kernel/iommu-common.c
index 59cb16691322..23ca75f09277 100644
--- a/arch/sparc/kernel/iommu-common.c
+++ b/arch/sparc/kernel/iommu-common.c
@@ -166,13 +166,6 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << iommu->table_shift);
-	else
-		boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift);
-
-	boundary_size = boundary_size >> iommu->table_shift;
 	/*
 	 * if the skip_span_boundary_check had been set during init, we set
 	 * things up so that iommu_is_span_boundary() merely checks if the
@@ -181,6 +174,9 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 	if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) {
 		shift = 0;
 		boundary_size = iommu->poolsize * iommu->nr_pools;
+	} else {
+		boundary_size = dma_get_seg_boundary_nr_pages(dev,
+					iommu->table_shift);
 	}
 	n = iommu_area_alloc(iommu->map, limit, start, npages, shift,
 			     boundary_size, align_mask);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 4ae7388b1bff..a034f571d869 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/errno.h>
 #include <linux/iommu-helper.h>
 #include <linux/bitmap.h>
@@ -472,8 +472,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	outs->dma_length = 0;
 
 	max_seg_size = dma_get_max_seg_size(dev);
-	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index d6874c9b639f..8e1d72a16759 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -38,7 +38,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of_device.h>
 
 #include <asm/io.h>
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index dfbca2470536..217c21a6986a 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -453,6 +453,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)(regs->u_regs[UREG_RETPC] + 8);
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->u_regs[UREG_RETPC] =
@@ -465,58 +466,12 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 static int __kprobes trampoline_probe_handler(struct kprobe *p,
 					      struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
+	unsigned long orig_ret_address = 0;
 
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more than one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		if (ri->rp && ri->rp->handler)
-			ri->rp->handler(ri, regs);
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+	orig_ret_address = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
 	regs->tpc = orig_ret_address;
 	regs->tnpc = orig_ret_address + 4;
 
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
 	/*
 	 * By returning a non-zero value, we are telling
 	 * kprobe_handler() that we don't want the post_handler
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 14b93c5564e3..9de57e88f7a1 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/log2.h>
 #include <linux/of_device.h>
+#include <linux/dma-map-ops.h>
 #include <asm/iommu-common.h>
 
 #include <asm/iommu.h>
@@ -508,8 +509,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	iommu_batch_start(dev, prot, ~0UL);
 
 	max_seg_size = dma_get_max_seg_size(dev);
-	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 
 	mask = *dev->dma_mask;
 	if (!iommu_use_atu(iommu, mask))
diff --git a/arch/sparc/kernel/process.c b/arch/sparc/kernel/process.c
index 5234b5ccc0b9..0442ab00518d 100644
--- a/arch/sparc/kernel/process.c
+++ b/arch/sparc/kernel/process.c
@@ -25,7 +25,7 @@ asmlinkage long sparc_fork(struct pt_regs *regs)
 		.stack		= regs->u_regs[UREG_FP],
 	};
 
-	ret = _do_fork(&args);
+	ret = kernel_clone(&args);
 
 	/* If we get an error and potentially restart the system
 	 * call, we're screwed because copy_thread() clobbered
@@ -50,7 +50,7 @@ asmlinkage long sparc_vfork(struct pt_regs *regs)
 		.stack		= regs->u_regs[UREG_FP],
 	};
 
-	ret = _do_fork(&args);
+	ret = kernel_clone(&args);
 
 	/* If we get an error and potentially restart the system
 	 * call, we're screwed because copy_thread() clobbered
@@ -96,7 +96,7 @@ asmlinkage long sparc_clone(struct pt_regs *regs)
 	else
 		args.stack = regs->u_regs[UREG_FP];
 
-	ret = _do_fork(&args);
+	ret = kernel_clone(&args);
 
 	/* If we get an error and potentially restart the system
 	 * call, we're screwed because copy_thread() clobbered
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index e286e2badc8a..e38d8bf454e8 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1039,38 +1039,9 @@ void smp_fetch_global_pmu(void)
  * are flush_tlb_*() routines, and these run after flush_cache_*()
  * which performs the flushw.
  *
- * The SMP TLB coherency scheme we use works as follows:
- *
- * 1) mm->cpu_vm_mask is a bit mask of which cpus an address
- *    space has (potentially) executed on, this is the heuristic
- *    we use to avoid doing cross calls.
- *
- *    Also, for flushing from kswapd and also for clones, we
- *    use cpu_vm_mask as the list of cpus to make run the TLB.
- *
- * 2) TLB context numbers are shared globally across all processors
- *    in the system, this allows us to play several games to avoid
- *    cross calls.
- *
- *    One invariant is that when a cpu switches to a process, and
- *    that processes tsk->active_mm->cpu_vm_mask does not have the
- *    current cpu's bit set, that tlb context is flushed locally.
- *
- *    If the address space is non-shared (ie. mm->count == 1) we avoid
- *    cross calls when we want to flush the currently running process's
- *    tlb state.  This is done by clearing all cpu bits except the current
- *    processor's in current->mm->cpu_vm_mask and performing the
- *    flush locally only.  This will force any subsequent cpus which run
- *    this task to flush the context from the local tlb if the process
- *    migrates to another cpu (again).
- *
- * 3) For shared address spaces (threads) and swapping we bite the
- *    bullet for most cases and perform the cross call (but only to
- *    the cpus listed in cpu_vm_mask).
- *
- *    The performance gain from "optimizing" away the cross call for threads is
- *    questionable (in theory the big win for threads is the massive sharing of
- *    address space state across processors).
+ * mm->cpu_vm_mask is a bit mask of which cpus an address
+ * space has (potentially) executed on, this is the heuristic
+ * we use to limit cross calls.
  */
 
 /* This currently is only used by the hugetlb arch pre-fault
@@ -1080,18 +1051,13 @@ void smp_fetch_global_pmu(void)
 void smp_flush_tlb_mm(struct mm_struct *mm)
 {
 	u32 ctx = CTX_HWBITS(mm->context);
-	int cpu = get_cpu();
 
-	if (atomic_read(&mm->mm_users) == 1) {
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-		goto local_flush_and_out;
-	}
+	get_cpu();
 
 	smp_cross_call_masked(&xcall_flush_tlb_mm,
 			      ctx, 0, 0,
 			      mm_cpumask(mm));
 
-local_flush_and_out:
 	__flush_tlb_mm(ctx, SECONDARY_CONTEXT);
 
 	put_cpu();
@@ -1114,17 +1080,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long
 {
 	u32 ctx = CTX_HWBITS(mm->context);
 	struct tlb_pending_info info;
-	int cpu = get_cpu();
+
+	get_cpu();
 
 	info.ctx = ctx;
 	info.nr = nr;
 	info.vaddrs = vaddrs;
 
-	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-	else
-		smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
-				       &info, 1);
+	smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+			       &info, 1);
 
 	__flush_tlb_pending(ctx, nr, vaddrs);
 
@@ -1134,14 +1098,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long
 void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
 {
 	unsigned long context = CTX_HWBITS(mm->context);
-	int cpu = get_cpu();
 
-	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
-		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
-	else
-		smp_cross_call_masked(&xcall_flush_tlb_page,
-				      context, vaddr, 0,
-				      mm_cpumask(mm));
+	get_cpu();
+
+	smp_cross_call_masked(&xcall_flush_tlb_page,
+			      context, vaddr, 0,
+			      mm_cpumask(mm));
+
 	__flush_tlb_page(context, vaddr);
 
 	put_cpu();
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4af114e84f20..78160260991b 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -38,7 +38,7 @@
 23	64    	setuid			sys_setuid
 24	32	getuid			sys_getuid16
 24	64   	getuid			sys_getuid
-25	common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+25	common	vmsplice		sys_vmsplice
 26	common	ptrace			sys_ptrace			compat_sys_ptrace
 27	common	alarm			sys_alarm
 28	common	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
@@ -149,8 +149,8 @@
 117	common	getrusage		sys_getrusage			compat_sys_getrusage
 118	common	getsockopt		sys_getsockopt			sys_getsockopt
 119	common	getcwd			sys_getcwd
-120	common	readv			sys_readv			compat_sys_readv
-121	common	writev			sys_writev			compat_sys_writev
+120	common	readv			sys_readv
+121	common	writev			sys_writev
 122	common	settimeofday		sys_settimeofday		compat_sys_settimeofday
 123	32	fchown			sys_fchown16
 123	64	fchown			sys_fchown
@@ -201,7 +201,7 @@
 164	64	utrap_install		sys_utrap_install
 165	common	quotactl		sys_quotactl
 166	common	set_tid_address		sys_set_tid_address
-167	common	mount			sys_mount			compat_sys_mount
+167	common	mount			sys_mount
 168	common	ustat			sys_ustat			compat_sys_ustat
 169	common	setxattr		sys_setxattr
 170	common	lsetxattr		sys_lsetxattr
@@ -406,8 +406,8 @@
 335	common	syncfs			sys_syncfs
 336	common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
 337	common	setns			sys_setns
-338	common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-339	common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+338	common	process_vm_readv	sys_process_vm_readv
+339	common	process_vm_writev	sys_process_vm_writev
 340	32	kern_features		sys_ni_syscall			sys_kern_features
 340	64	kern_features		sys_kern_features
 341	common	kcmp			sys_kcmp
@@ -485,3 +485,4 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index f99e99e58075..d55ae65a07ad 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -187,6 +187,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }