Merge branch 'perf/urgent' into perf/core, to pick up fixes

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

14 files changed, 70 insertions, 35 deletions

diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 1a951b00465d..1fffbba8d6a5 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex);
 
 extern unsigned int rtas_data;
 extern unsigned long long memory_limit;
+extern bool init_mem_is_free;
 extern unsigned long klimit;
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ea04dfb8c092..2d8fc8c9da7a 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1314,9 +1314,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100)
 
 #ifdef CONFIG_PPC_DENORMALISATION
 	mfspr	r10,SPRN_HSRR1
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
 	andis.	r10,r10,(HSRR1_DENORM)@h /* denorm? */
-	addi	r11,r11,-4		/* HSRR0 is next instruction */
 	bne+	denorm_assist
 #endif
 
@@ -1382,6 +1380,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
  */
 	XVCPSGNDP32(32)
 denorm_done:
+	mfspr	r11,SPRN_HSRR0
+	subi	r11,r11,4
 	mtspr	SPRN_HSRR0,r11
 	mtcrf	0x80,r9
 	ld	r9,PACA_EXGEN+EX_R9(r13)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 6bffbc5affe7..7716374786bd 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -176,13 +176,27 @@ _GLOBAL(tm_reclaim)
 	std	r1, PACATMSCRATCH(r13)
 	ld	r1, PACAR1(r13)
 
-	/* Store the PPR in r11 and reset to decent value */
 	std	r11, GPR11(r1)			/* Temporary stash */
 
+	/*
+	 * Move the saved user r1 to the kernel stack in case PACATMSCRATCH is
+	 * clobbered by an exception once we turn on MSR_RI below.
+	 */
+	ld	r11, PACATMSCRATCH(r13)
+	std	r11, GPR1(r1)
+
+	/*
+	 * Store r13 away so we can free up the scratch SPR for the SLB fault
+	 * handler (needed once we start accessing the thread_struct).
+	 */
+	GET_SCRATCH0(r11)
+	std	r11, GPR13(r1)
+
 	/* Reset MSR RI so we can take SLB faults again */
 	li	r11, MSR_RI
 	mtmsrd	r11, 1
 
+	/* Store the PPR in r11 and reset to decent value */
 	mfspr	r11, SPRN_PPR
 	HMT_MEDIUM
 
@@ -207,11 +221,11 @@ _GLOBAL(tm_reclaim)
 	SAVE_GPR(8, r7)				/* user r8 */
 	SAVE_GPR(9, r7)				/* user r9 */
 	SAVE_GPR(10, r7)			/* user r10 */
-	ld	r3, PACATMSCRATCH(r13)		/* user r1 */
+	ld	r3, GPR1(r1)			/* user r1 */
 	ld	r4, GPR7(r1)			/* user r7 */
 	ld	r5, GPR11(r1)			/* user r11 */
 	ld	r6, GPR12(r1)			/* user r12 */
-	GET_SCRATCH0(8)				/* user r13 */
+	ld	r8, GPR13(r1)			/* user r13 */
 	std	r3, GPR1(r7)
 	std	r4, GPR7(r7)
 	std	r5, GPR11(r7)
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 886ed94b9c13..d05c8af4ac51 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -443,6 +443,9 @@ _GLOBAL(csum_ipv6_magic)
 	addc	r0, r8, r9
 	ld	r10, 0(r4)
 	ld	r11, 8(r4)
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	rotldi	r5, r5, 8
+#endif
 	adde	r0, r0, r10
 	add	r5, r5, r7
 	adde	r0, r0, r11
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 850f3b8f4da5..6ae2777c220d 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -28,6 +28,12 @@ static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
 {
 	int err;
 
+	/* Make sure we aren't patching a freed init section */
+	if (init_mem_is_free && init_section_contains(exec_addr, 4)) {
+		pr_debug("Skipping init section patching addr: 0x%px\n", exec_addr);
+		return 0;
+	}
+
 	__put_user_size(instr, patch_addr, 4, err);
 	if (err)
 		return err;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 5c8530d0c611..04ccb274a620 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -63,6 +63,7 @@
 #endif
 
 unsigned long long memory_limit;
+bool init_mem_is_free;
 
 #ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
@@ -396,6 +397,7 @@ void free_initmem(void)
 {
 	ppc_md.progress = ppc_printk_progress;
 	mark_initmem_nx();
+	init_mem_is_free = true;
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 35ac5422903a..59d07bd5374a 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1204,7 +1204,9 @@ int find_and_online_cpu_nid(int cpu)
 	int new_nid;
 
 	/* Use associativity from first thread for all siblings */
-	vphn_get_associativity(cpu, associativity);
+	if (vphn_get_associativity(cpu, associativity))
+		return cpu_to_node(cpu);
+
 	new_nid = associativity_to_nid(associativity);
 	if (new_nid < 0 || !node_possible(new_nid))
 		new_nid = first_online_node;
@@ -1452,7 +1454,8 @@ static struct timer_list topology_timer;
 
 static void reset_topology_timer(void)
 {
-	mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
+	if (vphn_enabled)
+		mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c
index 333b1f80c435..b271b283c785 100644
--- a/arch/powerpc/mm/pkeys.c
+++ b/arch/powerpc/mm/pkeys.c
@@ -45,7 +45,7 @@ static void scan_pkey_feature(void)
 	 * Since any pkey can be used for data or execute, we will just treat
 	 * all keys as equal and track them as one entity.
 	 */
-	pkeys_total = be32_to_cpu(vals[0]);
+	pkeys_total = vals[0];
 	pkeys_devtree_defined = true;
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
index 6c5db1acbe8d..fe9691040f54 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
@@ -276,7 +276,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 	level_shift = entries_shift + 3;
 	level_shift = max_t(unsigned int, level_shift, PAGE_SHIFT);
 
-	if ((level_shift - 3) * levels + page_shift >= 60)
+	if ((level_shift - 3) * levels + page_shift >= 55)
 		return -EINVAL;
 
 	/* Allocate TCE table */
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..c9fecd120d18
--- /dev/null
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_PROTOTYPES_H
+
+#include <linux/ftrace.h>
+#include <asm-generic/asm-prototypes.h>
+
+#endif /* _ASM_RISCV_PROTOTYPES_H */
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index eaa843a52907..a480356e0ed8 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -25,20 +25,6 @@ ENTRY(get_sev_encryption_bit)
 	push	%ebx
 	push	%ecx
 	push	%edx
-	push	%edi
-
-	/*
-	 * RIP-relative addressing is needed to access the encryption bit
-	 * variable. Since we are running in 32-bit mode we need this call/pop
-	 * sequence to get the proper relative addressing.
-	 */
-	call	1f
-1:	popl	%edi
-	subl	$1b, %edi
-
-	movl	enc_bit(%edi), %eax
-	cmpl	$0, %eax
-	jge	.Lsev_exit
 
 	/* Check if running under a hypervisor */
 	movl	$1, %eax
@@ -69,15 +55,12 @@ ENTRY(get_sev_encryption_bit)
 
 	movl	%ebx, %eax
 	andl	$0x3f, %eax		/* Return the encryption bit location */
-	movl	%eax, enc_bit(%edi)
 	jmp	.Lsev_exit
 
 .Lno_sev:
 	xor	%eax, %eax
-	movl	%eax, enc_bit(%edi)
 
 .Lsev_exit:
-	pop	%edi
 	pop	%edx
 	pop	%ecx
 	pop	%ebx
@@ -113,8 +96,6 @@ ENTRY(set_sev_encryption_mask)
 ENDPROC(set_sev_encryption_mask)
 
 	.data
-enc_bit:
-	.int	0xffffffff
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	.balign	8
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 981ba5e8241b..8671de126eac 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -36,6 +36,7 @@
 
 static int num_counters_llc;
 static int num_counters_nb;
+static bool l3_mask;
 
 static HLIST_HEAD(uncore_unused_list);
 
@@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event)
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
+	/*
+	 * SliceMask and ThreadMask need to be set for certain L3 events in
+	 * Family 17h. For other events, the two fields do not affect the count.
+	 */
+	if (l3_mask)
+		hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -525,6 +533,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l3";
 		format_attr_event_df.show = &event_show_df;
 		format_attr_event_l3.show = &event_show_l3;
+		l3_mask			  = true;
 	} else {
 		num_counters_nb		  = NUM_COUNTERS_NB;
 		num_counters_llc	  = NUM_COUNTERS_L2;
@@ -532,6 +541,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l2";
 		format_attr_event_df	  = format_attr_event;
 		format_attr_event_l3	  = format_attr_event;
+		l3_mask			  = false;
 	}
 
 	amd_nb_pmu.attr_groups	= amd_uncore_attr_groups_df;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 51d7c117e3c7..c07bee31abe8 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
 
 void bdx_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id);
 
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
@@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = {
 		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
 	},
 	{ /* M3UPI0 Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0),
 	},
 	{ /* M3UPI0 Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1),
 	},
 	{ /* M3UPI1 Link 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2),
 	},
 	{ /* end: all zeroes */ }
 };
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 12f54082f4c8..78241b736f2a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -46,6 +46,14 @@
 #define INTEL_ARCH_EVENT_MASK	\
 	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
 
+#define AMD64_L3_SLICE_SHIFT				48
+#define AMD64_L3_SLICE_MASK				\
+	((0xFULL) << AMD64_L3_SLICE_SHIFT)
+
+#define AMD64_L3_THREAD_SHIFT				56
+#define AMD64_L3_THREAD_MASK				\
+	((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+
 #define X86_RAW_EVENT_MASK		\
 	(ARCH_PERFMON_EVENTSEL_EVENT |	\
 	 ARCH_PERFMON_EVENTSEL_UMASK |	\