Merge tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "A bit of a small release, I suspect in part due to me travelling for
  KS. But my backlog of patches to review is smaller than usual, so I
  think in part folks just didn't send as much this cycle.

  Non-highlights:

   - Five fixes for the >128T address space handling, both to fix bugs
     in our implementation and to bring the semantics exactly into line
     with x86.

  Highlights:

   - Support for a new OPAL call on bare metal machines which gives us a
     true NMI (ie. is not masked by MSR[EE]=0) for debugging etc.

   - Support for Power9 DD2 in the CXL driver.

   - Improvements to machine check handling so that uncorrectable errors
     can be reported into the generic memory_failure() machinery.

   - Some fixes and improvements for VPHN, which is used under PowerVM
     to notify the Linux partition of topology changes.

   - Plumbing to enable TM (transactional memory) without suspend on
     some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND).

   - Support for emulating vector loads form cache-inhibited memory, on
     some Power9 revisions.

   - Disable the fast-endian switch "syscall" by default (behind a
     CONFIG), we believe it has never had any users.

   - A major rework of the API drivers use when initiating and waiting
     for long running operations performed by OPAL firmware, and changes
     to the powernv_flash driver to use the new API.

   - Several fixes for the handling of FP/VMX/VSX while processes are
     using transactional memory.

   - Optimisations of TLB range flushes when using the radix MMU on
     Power9.

   - Improvements to the VAS facility used to access coprocessors on
     Power9, and related improvements to the way the NX crypto driver
     handles requests.

   - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit.

  Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew
  Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin
  Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard,
  Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven,
  Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley,
  Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu,
  Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao,
  Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia
  Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee,
  Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel
  Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A.
  Kennington III"

* tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits)
  powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature
  powerpc/64s: Fix masking of SRR1 bits on instruction fault
  powerpc/64s: mm_context.addr_limit is only used on hash
  powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary
  powerpc/64s/hash: Fix fork() with 512TB process address space
  powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Fix 512T hint detection to use >= 128T
  powerpc: Fix DABR match on hash based systems
  powerpc/signal: Properly handle return value from uprobe_deny_signal()
  powerpc/fadump: use kstrtoint to handle sysfs store
  powerpc/lib: Implement UACCESS_FLUSHCACHE API
  powerpc/lib: Implement PMEM API
  powerpc/powernv/npu: Don't explicitly flush nmmu tlb
  powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm()
  powerpc/powernv/idle: Round up latency and residency values
  powerpc/kprobes: refactor kprobe_lookup_name for safer string operations
  powerpc/kprobes: Blacklist emulate_update_regs() from kprobes
  powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace
  powerpc/kprobes: Disable preemption before invoking probe handler for optprobes
  ...

1 files changed, 247 insertions, 100 deletions

diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index d304028641a2..884f4b705b57 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -39,6 +39,20 @@ static inline void __tlbiel_pid(unsigned long pid, int set,
 	trace_tlbie(0, 1, rb, rs, ric, prs, r);
 }
 
+static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
+{
+	unsigned long rb,rs,prs,r;
+
+	rb = PPC_BIT(53); /* IS = 1 */
+	rs = pid << PPC_BITLSHIFT(31);
+	prs = 1; /* process scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
@@ -70,22 +84,13 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 
 static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
-	unsigned long rb,rs,prs,r;
-
-	rb = PPC_BIT(53); /* IS = 1 */
-	rs = pid << PPC_BITLSHIFT(31);
-	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
-
 	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	__tlbie_pid(pid, ric);
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
-static inline void _tlbiel_va(unsigned long va, unsigned long pid,
-			      unsigned long ap, unsigned long ric)
+static inline void __tlbiel_va(unsigned long va, unsigned long pid,
+			       unsigned long ap, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
@@ -95,14 +100,44 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
 
-	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	asm volatile("ptesync": : :"memory");
 	trace_tlbie(0, 1, rb, rs, ric, prs, r);
 }
 
-static inline void _tlbie_va(unsigned long va, unsigned long pid,
+static inline void __tlbiel_va_range(unsigned long start, unsigned long end,
+				    unsigned long pid, unsigned long page_size,
+				    unsigned long psize)
+{
+	unsigned long addr;
+	unsigned long ap = mmu_get_ap(psize);
+
+	for (addr = start; addr < end; addr += page_size)
+		__tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
+}
+
+static inline void _tlbiel_va(unsigned long va, unsigned long pid,
+			      unsigned long psize, unsigned long ric)
+{
+	unsigned long ap = mmu_get_ap(psize);
+
+	asm volatile("ptesync": : :"memory");
+	__tlbiel_va(va, pid, ap, ric);
+	asm volatile("ptesync": : :"memory");
+}
+
+static inline void _tlbiel_va_range(unsigned long start, unsigned long end,
+				    unsigned long pid, unsigned long page_size,
+				    unsigned long psize, bool also_pwc)
+{
+	asm volatile("ptesync": : :"memory");
+	if (also_pwc)
+		__tlbiel_pid(pid, 0, RIC_FLUSH_PWC);
+	__tlbiel_va_range(start, end, pid, page_size, psize);
+	asm volatile("ptesync": : :"memory");
+}
+
+static inline void __tlbie_va(unsigned long va, unsigned long pid,
 			     unsigned long ap, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
@@ -113,13 +148,43 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
 
-	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void __tlbie_va_range(unsigned long start, unsigned long end,
+				    unsigned long pid, unsigned long page_size,
+				    unsigned long psize)
+{
+	unsigned long addr;
+	unsigned long ap = mmu_get_ap(psize);
+
+	for (addr = start; addr < end; addr += page_size)
+		__tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
+}
+
+static inline void _tlbie_va(unsigned long va, unsigned long pid,
+			      unsigned long psize, unsigned long ric)
+{
+	unsigned long ap = mmu_get_ap(psize);
+
+	asm volatile("ptesync": : :"memory");
+	__tlbie_va(va, pid, ap, ric);
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+
+static inline void _tlbie_va_range(unsigned long start, unsigned long end,
+				    unsigned long pid, unsigned long page_size,
+				    unsigned long psize, bool also_pwc)
+{
+	asm volatile("ptesync": : :"memory");
+	if (also_pwc)
+		__tlbie_pid(pid, RIC_FLUSH_PWC);
+	__tlbie_va_range(start, end, pid, page_size, psize);
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+
 /*
  * Base TLB flushing operations:
  *
@@ -144,7 +209,7 @@ void radix__local_flush_tlb_mm(struct mm_struct *mm)
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
 
 #ifndef CONFIG_SMP
-static void radix__local_flush_all_mm(struct mm_struct *mm)
+void radix__local_flush_all_mm(struct mm_struct *mm)
 {
 	unsigned long pid;
 
@@ -154,18 +219,18 @@ static void radix__local_flush_all_mm(struct mm_struct *mm)
 		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 	preempt_enable();
 }
+EXPORT_SYMBOL(radix__local_flush_all_mm);
 #endif /* CONFIG_SMP */
 
 void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 				       int psize)
 {
 	unsigned long pid;
-	unsigned long ap = mmu_get_ap(psize);
 
 	preempt_disable();
-	pid = mm ? mm->context.id : 0;
+	pid = mm->context.id;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
+		_tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
 	preempt_enable();
 }
 
@@ -173,11 +238,10 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd
 {
 #ifdef CONFIG_HUGETLB_PAGE
 	/* need the return fix for nohash.c */
-	if (vma && is_vm_hugetlb_page(vma))
-		return __local_flush_hugetlb_page(vma, vmaddr);
+	if (is_vm_hugetlb_page(vma))
+		return radix__local_flush_hugetlb_page(vma, vmaddr);
 #endif
-	radix__local_flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr,
-					  mmu_virtual_psize);
+	radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, mmu_virtual_psize);
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_page);
 
@@ -186,36 +250,35 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 {
 	unsigned long pid;
 
-	preempt_disable();
 	pid = mm->context.id;
 	if (unlikely(pid == MMU_NO_CONTEXT))
-		goto no_context;
+		return;
 
+	preempt_disable();
 	if (!mm_is_thread_local(mm))
 		_tlbie_pid(pid, RIC_FLUSH_TLB);
 	else
 		_tlbiel_pid(pid, RIC_FLUSH_TLB);
-no_context:
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
-static void radix__flush_all_mm(struct mm_struct *mm)
+void radix__flush_all_mm(struct mm_struct *mm)
 {
 	unsigned long pid;
 
-	preempt_disable();
 	pid = mm->context.id;
 	if (unlikely(pid == MMU_NO_CONTEXT))
-		goto no_context;
+		return;
 
+	preempt_disable();
 	if (!mm_is_thread_local(mm))
 		_tlbie_pid(pid, RIC_FLUSH_ALL);
 	else
 		_tlbiel_pid(pid, RIC_FLUSH_ALL);
-no_context:
 	preempt_enable();
 }
+EXPORT_SYMBOL(radix__flush_all_mm);
 
 void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
 {
@@ -227,28 +290,26 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 				 int psize)
 {
 	unsigned long pid;
-	unsigned long ap = mmu_get_ap(psize);
 
-	preempt_disable();
-	pid = mm ? mm->context.id : 0;
+	pid = mm->context.id;
 	if (unlikely(pid == MMU_NO_CONTEXT))
-		goto bail;
+		return;
+
+	preempt_disable();
 	if (!mm_is_thread_local(mm))
-		_tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
+		_tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
 	else
-		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
-bail:
+		_tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
 	preempt_enable();
 }
 
 void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
 #ifdef CONFIG_HUGETLB_PAGE
-	if (vma && is_vm_hugetlb_page(vma))
-		return flush_hugetlb_page(vma, vmaddr);
+	if (is_vm_hugetlb_page(vma))
+		return radix__flush_hugetlb_page(vma, vmaddr);
 #endif
-	radix__flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr,
-				    mmu_virtual_psize);
+	radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, mmu_virtual_psize);
 }
 EXPORT_SYMBOL(radix__flush_tlb_page);
 
@@ -262,17 +323,86 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
 }
 EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
 
+#define TLB_FLUSH_ALL -1UL
+
 /*
- * Currently, for range flushing, we just do a full mm flush. Because
- * we use this in code path where we don' track the page size.
+ * Number of pages above which we invalidate the entire PID rather than
+ * flush individual pages, for local and global flushes respectively.
+ *
+ * tlbie goes out to the interconnect and individual ops are more costly.
+ * It also does not iterate over sets like the local tlbiel variant when
+ * invalidating a full PID, so it has a far lower threshold to change from
+ * individual page flushes to full-pid flushes.
  */
+static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
+static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
+
 void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 
 {
 	struct mm_struct *mm = vma->vm_mm;
+	unsigned long pid;
+	unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift;
+	unsigned long page_size = 1UL << page_shift;
+	unsigned long nr_pages = (end - start) >> page_shift;
+	bool local, full;
+
+#ifdef CONFIG_HUGETLB_PAGE
+	if (is_vm_hugetlb_page(vma))
+		return radix__flush_hugetlb_tlb_range(vma, start, end);
+#endif
+
+	pid = mm->context.id;
+	if (unlikely(pid == MMU_NO_CONTEXT))
+		return;
 
-	radix__flush_tlb_mm(mm);
+	preempt_disable();
+	if (mm_is_thread_local(mm)) {
+		local = true;
+		full = (end == TLB_FLUSH_ALL ||
+				nr_pages > tlb_local_single_page_flush_ceiling);
+	} else {
+		local = false;
+		full = (end == TLB_FLUSH_ALL ||
+				nr_pages > tlb_single_page_flush_ceiling);
+	}
+
+	if (full) {
+		if (local)
+			_tlbiel_pid(pid, RIC_FLUSH_TLB);
+		else
+			_tlbie_pid(pid, RIC_FLUSH_TLB);
+	} else {
+		bool hflush = false;
+		unsigned long hstart, hend;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		hstart = (start + HPAGE_PMD_SIZE - 1) >> HPAGE_PMD_SHIFT;
+		hend = end >> HPAGE_PMD_SHIFT;
+		if (hstart < hend) {
+			hstart <<= HPAGE_PMD_SHIFT;
+			hend <<= HPAGE_PMD_SHIFT;
+			hflush = true;
+		}
+#endif
+
+		asm volatile("ptesync": : :"memory");
+		if (local) {
+			__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
+			if (hflush)
+				__tlbiel_va_range(hstart, hend, pid,
+						HPAGE_PMD_SIZE, MMU_PAGE_2M);
+			asm volatile("ptesync": : :"memory");
+		} else {
+			__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
+			if (hflush)
+				__tlbie_va_range(hstart, hend, pid,
+						HPAGE_PMD_SIZE, MMU_PAGE_2M);
+			asm volatile("eieio; tlbsync; ptesync": : :"memory");
+		}
+	}
+	preempt_enable();
 }
 EXPORT_SYMBOL(radix__flush_tlb_range);
 
@@ -291,101 +421,118 @@ static int radix_get_mmu_psize(int page_size)
 	return psize;
 }
 
+static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
+				  unsigned long end, int psize);
+
 void radix__tlb_flush(struct mmu_gather *tlb)
 {
 	int psize = 0;
 	struct mm_struct *mm = tlb->mm;
 	int page_size = tlb->page_size;
 
-	psize = radix_get_mmu_psize(page_size);
 	/*
 	 * if page size is not something we understand, do a full mm flush
+	 *
+	 * A "fullmm" flush must always do a flush_all_mm (RIC=2) flush
+	 * that flushes the process table entry cache upon process teardown.
+	 * See the comment for radix in arch_exit_mmap().
 	 */
-	if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all)
-		radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize);
-	else if (tlb->need_flush_all) {
-		tlb->need_flush_all = 0;
+	if (tlb->fullmm) {
 		radix__flush_all_mm(mm);
-	} else
-		radix__flush_tlb_mm(mm);
-}
+	} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
+		if (!tlb->need_flush_all)
+			radix__flush_tlb_mm(mm);
+		else
+			radix__flush_all_mm(mm);
+	} else {
+		unsigned long start = tlb->start;
+		unsigned long end = tlb->end;
 
-#define TLB_FLUSH_ALL -1UL
-/*
- * Number of pages above which we will do a bcast tlbie. Just a
- * number at this point copied from x86
- */
-static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
+		if (!tlb->need_flush_all)
+			radix__flush_tlb_range_psize(mm, start, end, psize);
+		else
+			radix__flush_tlb_pwc_range_psize(mm, start, end, psize);
+	}
+	tlb->need_flush_all = 0;
+}
 
-void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
-				  unsigned long end, int psize)
+static inline void __radix__flush_tlb_range_psize(struct mm_struct *mm,
+				unsigned long start, unsigned long end,
+				int psize, bool also_pwc)
 {
 	unsigned long pid;
-	unsigned long addr;
-	int local = mm_is_thread_local(mm);
-	unsigned long ap = mmu_get_ap(psize);
-	unsigned long page_size = 1UL << mmu_psize_defs[psize].shift;
+	unsigned int page_shift = mmu_psize_defs[psize].shift;
+	unsigned long page_size = 1UL << page_shift;
+	unsigned long nr_pages = (end - start) >> page_shift;
+	bool local, full;
 
+	pid = mm->context.id;
+	if (unlikely(pid == MMU_NO_CONTEXT))
+		return;
 
 	preempt_disable();
-	pid = mm ? mm->context.id : 0;
-	if (unlikely(pid == MMU_NO_CONTEXT))
-		goto err_out;
+	if (mm_is_thread_local(mm)) {
+		local = true;
+		full = (end == TLB_FLUSH_ALL ||
+				nr_pages > tlb_local_single_page_flush_ceiling);
+	} else {
+		local = false;
+		full = (end == TLB_FLUSH_ALL ||
+				nr_pages > tlb_single_page_flush_ceiling);
+	}
 
-	if (end == TLB_FLUSH_ALL ||
-	    (end - start) > tlb_single_page_flush_ceiling * page_size) {
+	if (full) {
 		if (local)
-			_tlbiel_pid(pid, RIC_FLUSH_TLB);
+			_tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
 		else
-			_tlbie_pid(pid, RIC_FLUSH_TLB);
-		goto err_out;
-	}
-	for (addr = start; addr < end; addr += page_size) {
-
+			_tlbie_pid(pid, also_pwc ? RIC_FLUSH_ALL: RIC_FLUSH_TLB);
+	} else {
 		if (local)
-			_tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
+			_tlbiel_va_range(start, end, pid, page_size, psize, also_pwc);
 		else
-			_tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
+			_tlbie_va_range(start, end, pid, page_size, psize, also_pwc);
 	}
-err_out:
 	preempt_enable();
 }
 
+void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
+				  unsigned long end, int psize)
+{
+	return __radix__flush_tlb_range_psize(mm, start, end, psize, false);
+}
+
+static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
+				  unsigned long end, int psize)
+{
+	__radix__flush_tlb_range_psize(mm, start, end, psize, true);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
 {
-	int local = mm_is_thread_local(mm);
-	unsigned long ap = mmu_get_ap(mmu_virtual_psize);
 	unsigned long pid, end;
 
-
-	pid = mm ? mm->context.id : 0;
-	preempt_disable();
+	pid = mm->context.id;
 	if (unlikely(pid == MMU_NO_CONTEXT))
-		goto no_context;
+		return;
 
 	/* 4k page size, just blow the world */
 	if (PAGE_SIZE == 0x1000) {
 		radix__flush_all_mm(mm);
-		preempt_enable();
 		return;
 	}
 
-	/* Otherwise first do the PWC */
-	if (local)
-		_tlbiel_pid(pid, RIC_FLUSH_PWC);
-	else
-		_tlbie_pid(pid, RIC_FLUSH_PWC);
-
-	/* Then iterate the pages */
 	end = addr + HPAGE_PMD_SIZE;
-	for (; addr < end; addr += PAGE_SIZE) {
-		if (local)
-			_tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
-		else
-			_tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
+
+	/* Otherwise first do the PWC, then iterate the pages. */
+	preempt_disable();
+
+	if (mm_is_thread_local(mm)) {
+		_tlbiel_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
+	} else {
+		_tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
 	}
-no_context:
+
 	preempt_enable();
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */