Merge tag 'powerpc-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - A series from Nick adding ARCH_WANT_IRQS_OFF_ACTIVATE_MM & selecting
   it for powerpc, as well as a related fix for sparc.

 - Remove support for PowerPC 601.

 - Some fixes for watchpoints & addition of a new ptrace flag for
   detecting ISA v3.1 (Power10) watchpoint features.

 - A fix for kernels using 4K pages and the hash MMU on bare metal
   Power9 systems with > 16TB of RAM, or RAM on the 2nd node.

 - A basic idle driver for shallow stop states on Power10.

 - Tweaks to our sched domains code to better inform the scheduler about
   the hardware topology on Power9/10, where two SMT4 cores can be
   presented by firmware as an SMT8 core.

 - A series doing further reworks & cleanups of our EEH code.

 - Addition of a filter for RTAS (firmware) calls done via sys_rtas(),
   to prevent root from overwriting kernel memory.

 - Other smaller features, fixes & cleanups.

Thanks to: Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V,
Athira Rajeev, Biwen Li, Cameron Berkenpas, Cédric Le Goater, Christophe
Leroy, Christoph Hellwig, Colin Ian King, Daniel Axtens, David Dai, Finn
Thain, Frederic Barrat, Gautham R. Shenoy, Greg Kurz, Gustavo Romero,
Ira Weiny, Jason Yan, Joel Stanley, Jordan Niethe, Kajol Jain, Konrad
Rzeszutek Wilk, Laurent Dufour, Leonardo Bras, Liu Shixin, Luca
Ceresoli, Madhavan Srinivasan, Mahesh Salgaonkar, Nathan Lynch, Nicholas
Mc Guire, Nicholas Piggin, Nick Desaulniers, Oliver O'Halloran, Pedro
Miraglia Franco de Carvalho, Pratik Rajesh Sampat, Qian Cai, Qinglang
Miao, Ravi Bangoria, Russell Currey, Satheesh Rajendran, Scott Cheloha,
Segher Boessenkool, Srikar Dronamraju, Stan Johnson, Stephen Kitt,
Stephen Rothwell, Thiago Jung Bauermann, Tyrel Datwyler, Vaibhav Jain,
Vaidyanathan Srinivasan, Vasant Hegde, Wang Wensheng, Wolfram Sang, Yang
Yingliang, zhengbin.

* tag 'powerpc-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (228 commits)
  Revert "powerpc/pci: unmap legacy INTx interrupts when a PHB is removed"
  selftests/powerpc: Fix eeh-basic.sh exit codes
  cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_reboot_notifier
  powerpc/time: Make get_tb() common to PPC32 and PPC64
  powerpc/time: Make get_tbl() common to PPC32 and PPC64
  powerpc/time: Remove get_tbu()
  powerpc/time: Avoid using get_tbl() and get_tbu() internally
  powerpc/time: Make mftb() common to PPC32 and PPC64
  powerpc/time: Rename mftbl() to mftb()
  powerpc/32s: Remove #ifdef CONFIG_PPC_BOOK3S_32 in head_book3s_32.S
  powerpc/32s: Rename head_32.S to head_book3s_32.S
  powerpc/32s: Setup the early hash table at all time.
  powerpc/time: Remove ifdef in get_dec() and set_dec()
  powerpc: Remove get_tb_or_rtc()
  powerpc: Remove __USE_RTC()
  powerpc: Tidy up a bit after removal of PowerPC 601.
  powerpc: Remove support for PowerPC 601
  powerpc: Remove PowerPC 601
  powerpc: Drop SYNC_601() ISYNC_601() and SYNC()
  powerpc: Remove CONFIG_PPC601_SYNC_FIX
  ...

1 files changed, 14 insertions, 51 deletions

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();