powerpc fixes for 5.9 #5

Opt us out of the DEBUG_VM_PGTABLE support for now as it's causing crashes.
 
 Fix a long standing bug in our DMA mask handling that was hidden until recently,
 and which caused problems with some drivers.
 
 Fix a boot failure on systems with large amounts of RAM, and no hugepage support
 and using Radix MMU, only seen in the lab.
 
 A few other minor fixes.
 
 Thanks to:
   Alexey Kardashevskiy, Aneesh Kumar K.V, Gautham R. Shenoy, Hari Bathini, Ira
   Weiny, Nick Desaulniers, Shirisha Ganta, Vaibhav Jain, Vaidyanathan
   Srinivasan.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEJFGtCPCthwEv2Y/bUevqPMjhpYAFAl9kk4UTHG1wZUBlbGxl
 cm1hbi5pZC5hdQAKCRBR6+o8yOGlgLM5D/42Wuuq6hOpGEfE2XjBjsOxCR07SCw9
 CQ/c72jw/1tDLe0YclPVYAZc8BmT8uLo6tE2Ot+0vI+1Y06rRvC5g5uQBwp1zD/t
 MOwC0d4zf8a7WzBCcVaBv9HMHVOaKaTBwQc2R4k6NzYtARIf5m0evMPOWINioRsv
 /x4+Np8aeQd1WiVn6PBdqL8w1yRhk8LsVDvX35lFzQlgZvH09umXSGjw9K442xdE
 lr1PrV9GKd4DeudwLHPkMNs8Ul1QTxmY5vKIAklsJ5g3dBySfM7+GMrTzYOHYkWr
 aqGfGH6ojdFSQZRo7QwFhO52Kni7JN7AIoUPEBDqLb1fR10w8wesdjCs8JQMXIMc
 8Eo210EbiSsq6kG/LzqZuStLUAup3rQd20+wWua7jo8HbcZOLDH7pPGwNtJInPTr
 gwH7sALYhTzFUAO4LzqVVE+yA8wndFPHoz+QSkO6LZJKuszON2LJ0r+IEx1l9Wmr
 ClZYujK36/N+ih42xBFcBZi2lL0VKzlkn7u7NDeZQBONgoJMCoWkGDkEHnMI9zdT
 1iYcVZyY+IpJLcwxH+NP8weJKHIZbP4kvuFXR/QIpHdrDWKaTT95BvBhAK1KMYBo
 lLo81zMTzJCz2wWDg/+3sLuEzHdGr//uxcVXxjqE2vyEckeuZjiCyz0dRNEY4Sw3
 vB2p3Zl7L0J4pQ==
 =cj6B
 -----END PGP SIGNATURE-----

Merge tag 'powerpc-5.9-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "Some more powerpc fixes for 5.9:

   - Opt us out of the DEBUG_VM_PGTABLE support for now as it's causing
     crashes.

   - Fix a long standing bug in our DMA mask handling that was hidden
     until recently, and which caused problems with some drivers.

   - Fix a boot failure on systems with large amounts of RAM, and no
     hugepage support and using Radix MMU, only seen in the lab.

   - A few other minor fixes.

  Thanks to Alexey Kardashevskiy, Aneesh Kumar K.V, Gautham R. Shenoy,
  Hari Bathini, Ira Weiny, Nick Desaulniers, Shirisha Ganta, Vaibhav
  Jain, and Vaidyanathan Srinivasan"

* tag 'powerpc-5.9-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/papr_scm: Limit the readability of 'perf_stats' sysfs attribute
  cpuidle: pseries: Fix CEDE latency conversion from tb to us
  powerpc/dma: Fix dma_map_ops::get_required_mask
  Revert "powerpc/build: vdso linker warning for orphan sections"
  powerpc/mm: Remove DEBUG_VM_PGTABLE support on powerpc
  selftests/powerpc: Skip PROT_SAO test in guests/LPARS
  powerpc/book3s64/radix: Fix boot failure with large amount of guest memory

Documentation/features/debug/debug-vm-pgtable/arch-support.txt

@@ -22,7 +22,7 @@
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
-    |     powerpc: |  ok  |
+    |     powerpc: | TODO |
     |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: | TODO |

arch/powerpc/Kconfig

@@ -116,7 +116,6 @@ config PPC
 	#
 	select ARCH_32BIT_OFF_T if PPC32
 	select ARCH_HAS_DEBUG_VIRTUAL
-	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE

arch/powerpc/include/asm/book3s/64/mmu.h

@@ -239,14 +239,14 @@ static inline void early_init_mmu_secondary(void)
 
 extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
 					 phys_addr_t first_memblock_size);
-extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
-					 phys_addr_t first_memblock_size);
 static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 					      phys_addr_t first_memblock_size)
 {
-	if (early_radix_enabled())
-		return radix__setup_initial_memory_limit(first_memblock_base,
-						   first_memblock_size);
+	/*
+	 * Hash has more strict restrictions. At this point we don't
+	 * know which translations we will pick. Hence go with hash
+	 * restrictions.
+	 */
 	return hash__setup_initial_memory_limit(first_memblock_base,
 					   first_memblock_size);
 }

arch/powerpc/kernel/dma-iommu.c

@@ -120,7 +120,8 @@ u64 dma_iommu_get_required_mask(struct device *dev)
 	if (!tbl)
 		return 0;
 
-	mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
+	mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) +
+			tbl->it_page_shift - 1);
 	mask += mask - 1;
 
 	return mask;

arch/powerpc/kernel/vdso32/Makefile

@@ -50,7 +50,7 @@ $(obj-vdso32): %.o: %.S FORCE
 
 # actual build commands
 quiet_cmd_vdso32ld = VDSO32L $@
-      cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
+      cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $<
 

arch/powerpc/kernel/vdso32/vdso32.lds.S

@@ -111,7 +111,6 @@ SECTIONS
 		*(.note.GNU-stack)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
-		*(.glink .iplt .plt .rela*)
 	}
 }
 

arch/powerpc/kernel/vdso64/Makefile

@@ -34,7 +34,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 
 # actual build commands
 quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn)
+      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 
 # install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@

arch/powerpc/kernel/vdso64/vdso64.lds.S

@@ -30,7 +30,7 @@ SECTIONS
 	. = ALIGN(16);
 	.text		: {
 		*(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*)
-		*(.sfpr)
+		*(.sfpr .glink)
 	}						:text
 	PROVIDE(__etext = .);
 	PROVIDE(_etext = .);
@@ -111,7 +111,6 @@ SECTIONS
 		*(.branch_lt)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
-		*(.glink .iplt .plt .rela*)
 	}
 }
 

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -734,21 +734,6 @@ void radix__mmu_cleanup_all(void)
 	}
 }
 
-void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
-				phys_addr_t first_memblock_size)
-{
-	/*
-	 * We don't currently support the first MEMBLOCK not mapping 0
-	 * physical on those processors
-	 */
-	BUG_ON(first_memblock_base != 0);
-
-	/*
-	 * Radix mode is not limited by RMA / VRMA addressing.
-	 */
-	ppc64_rma_size = ULONG_MAX;
-}
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 static void free_pte_table(pte_t *pte_start, pmd_t *pmd)
 {

arch/powerpc/mm/init_64.c

@@ -433,9 +433,16 @@ void __init mmu_early_init_devtree(void)
 	if (!(mfmsr() & MSR_HV))
 		early_check_vec5();
 
-	if (early_radix_enabled())
+	if (early_radix_enabled()) {
 		radix__early_init_devtree();
-	else
+		/*
+		 * We have finalized the translation we are going to use by now.
+		 * Radix mode is not limited by RMA / VRMA addressing.
+		 * Hence don't limit memblock allocations.
+		 */
+		ppc64_rma_size = ULONG_MAX;
+		memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
+	} else
 		hash__early_init_devtree();
 }
 #endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/platforms/pseries/papr_scm.c

@@ -822,7 +822,7 @@ static ssize_t perf_stats_show(struct device *dev,
 	kfree(stats);
 	return rc ? rc : seq_buf_used(&s);
 }
-DEVICE_ATTR_RO(perf_stats);
+DEVICE_ATTR_ADMIN_RO(perf_stats);
 
 static ssize_t flags_show(struct device *dev,
 			  struct device_attribute *attr, char *buf)

drivers/cpuidle/cpuidle-pseries.c

@@ -361,7 +361,10 @@ static void __init fixup_cede0_latency(void)
 	for (i = 0; i < nr_xcede_records; i++) {
 		struct xcede_latency_record *record = &payload->records[i];
 		u64 latency_tb = be64_to_cpu(record->latency_ticks);
-		u64 latency_us = tb_to_ns(latency_tb) / NSEC_PER_USEC;
+		u64 latency_us = DIV_ROUND_UP_ULL(tb_to_ns(latency_tb), NSEC_PER_USEC);
+
+		if (latency_us == 0)
+			pr_warn("cpuidle: xcede record %d has an unrealistic latency of 0us.\n", i);
 
 		if (latency_us < min_latency_us)
 			min_latency_us = latency_us;
@@ -378,10 +381,14 @@ static void __init fixup_cede0_latency(void)
 	 * Perform the fix-up.
 	 */
 	if (min_latency_us < dedicated_states[1].exit_latency) {
-		u64 cede0_latency = min_latency_us - 1;
+		/*
+		 * We set a minimum of 1us wakeup latency for cede0 to
+		 * distinguish it from snooze
+		 */
+		u64 cede0_latency = 1;
 
-		if (cede0_latency <= 0)
-			cede0_latency = min_latency_us;
+		if (min_latency_us > cede0_latency)
+			cede0_latency = min_latency_us - 1;
 
 		dedicated_states[1].exit_latency = cede0_latency;
 		dedicated_states[1].target_residency = 10 * (cede0_latency);

tools/testing/selftests/powerpc/mm/prot_sao.c

@@ -7,6 +7,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/mman.h>
+#include <unistd.h>
 
 #include <asm/cputable.h>
 
@@ -18,9 +19,13 @@ int test_prot_sao(void)
 {
 	char *p;
 
-	/* SAO was introduced in 2.06 and removed in 3.1 */
+	/*
+	 * SAO was introduced in 2.06 and removed in 3.1. It's disabled in
+	 * guests/LPARs by default, so also skip if we are running in a guest.
+	 */
 	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06) ||
-		have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+		have_hwcap2(PPC_FEATURE2_ARCH_3_1) ||
+		access("/proc/device-tree/rtas/ibm,hypertas-functions", F_OK) == 0);
 
 	/*
 	 * Ensure we can ask for PROT_SAO.