13 files changed, 87 insertions, 46 deletions

diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 53be7ea6181b..9d2192156087 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -308,6 +308,29 @@ static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl,
 	return URC_OK;
 }
 
+static unsigned long unwind_decode_uleb128(struct unwind_ctrl_block *ctrl)
+{
+	unsigned long bytes = 0;
+	unsigned long insn;
+	unsigned long result = 0;
+
+	/*
+	 * unwind_get_byte() will advance `ctrl` one instruction at a time, so
+	 * loop until we get an instruction byte where bit 7 is not set.
+	 *
+	 * Note: This decodes a maximum of 4 bytes to output 28 bits data where
+	 * max is 0xfffffff: that will cover a vsp increment of 1073742336, hence
+	 * it is sufficient for unwinding the stack.
+	 */
+	do {
+		insn = unwind_get_byte(ctrl);
+		result |= (insn & 0x7f) << (bytes * 7);
+		bytes++;
+	} while (!!(insn & 0x80) && (bytes != sizeof(result)));
+
+	return result;
+}
+
 /*
  * Execute the current unwind instruction.
  */
@@ -361,7 +384,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 		if (ret)
 			goto error;
 	} else if (insn == 0xb2) {
-		unsigned long uleb128 = unwind_get_byte(ctrl);
+		unsigned long uleb128 = unwind_decode_uleb128(ctrl);
 
 		ctrl->vrs[SP] += 0x204 + (uleb128 << 2);
 	} else {
diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c
index 67f72ca984b2..1956b095e699 100644
--- a/arch/arm/mach-sa1100/jornada720_ssp.c
+++ b/arch/arm/mach-sa1100/jornada720_ssp.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  *  arch/arm/mac-sa1100/jornada720_ssp.c
  *
  *  Copyright (C) 2006/2007 Kristoffer Ericson <Kristoffer.Ericson@gmail.com>
@@ -26,6 +26,7 @@ static unsigned long jornada_ssp_flags;
 
 /**
  * jornada_ssp_reverse - reverses input byte
+ * @byte: input byte to reverse
  *
  * we need to reverse all data we receive from the mcu due to its physical location
  * returns : 01110111 -> 11101110
@@ -46,6 +47,7 @@ EXPORT_SYMBOL(jornada_ssp_reverse);
 
 /**
  * jornada_ssp_byte - waits for ready ssp bus and sends byte
+ * @byte: input byte to transmit
  *
  * waits for fifo buffer to clear and then transmits, if it doesn't then we will
  * timeout after <timeout> rounds. Needs mcu running before its called.
@@ -77,6 +79,7 @@ EXPORT_SYMBOL(jornada_ssp_byte);
 
 /**
  * jornada_ssp_inout - decide if input is command or trading byte
+ * @byte: input byte to send (may be %TXDUMMY)
  *
  * returns : (jornada_ssp_byte(byte)) on success
  *         : %-ETIMEDOUT on timeout failure
diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S
index 7483ef8bccda..62206ef25037 100644
--- a/arch/arm/vfp/entry.S
+++ b/arch/arm/vfp/entry.S
@@ -23,6 +23,9 @@
 @
 ENTRY(do_vfp)
 	mov	r1, r10
-	mov	r3, r9
-	b	vfp_entry
+	str	lr, [sp, #-8]!
+	add	r3, sp, #4
+	str	r9, [r3]
+	bl	vfp_entry
+	ldr	pc, [sp], #8
 ENDPROC(do_vfp)
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index 4d8478264d82..a4610d0f3215 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -172,13 +172,14 @@ vfp_hw_state_valid:
 					@ out before setting an FPEXC that
 					@ stops us reading stuff
 	VFPFMXR	FPEXC, r1		@ Restore FPEXC last
+	mov	sp, r3			@ we think we have handled things
+	pop	{lr}
 	sub	r2, r2, #4		@ Retry current instruction - if Thumb
 	str	r2, [sp, #S_PC]		@ mode it's two 16-bit instructions,
 					@ else it's one 32-bit instruction, so
 					@ always subtract 4 from the following
 					@ instruction address.
 
-	mov	lr, r3			@ we think we have handled things
 local_bh_enable_and_ret:
 	adr	r0, .
 	mov	r1, #SOFTIRQ_DISABLE_OFFSET
@@ -209,8 +210,9 @@ skip:
 
 process_exception:
 	DBGSTR	"bounce"
+	mov	sp, r3			@ setup for a return to the user code.
+	pop	{lr}
 	mov	r2, sp			@ nothing stacked - regdump is at TOS
-	mov	lr, r3			@ setup for a return to the user code.
 
 	@ Now call the C code to package up the bounce to the support code
 	@   r0 holds the trigger instruction
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index e2950f5db7c9..e715df5385d6 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -413,12 +413,12 @@ extern void paging_init (void);
  *   For the 64bit version, the offset is extended by 32bit.
  */
 #define __swp_type(x)                     ((x).val & 0x1f)
-#define __swp_offset(x)                   ( (((x).val >> 6) &  0x7) | \
-					  (((x).val >> 8) & ~0x7) )
+#define __swp_offset(x)                   ( (((x).val >> 5) & 0x7) | \
+					  (((x).val >> 10) << 3) )
 #define __swp_entry(type, offset)         ((swp_entry_t) { \
 					    ((type) & 0x1f) | \
-					    ((offset &  0x7) << 6) | \
-					    ((offset & ~0x7) << 8) })
+					    ((offset & 0x7) << 5) | \
+					    ((offset >> 3) << 10) })
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
diff --git a/arch/parisc/kernel/kexec.c b/arch/parisc/kernel/kexec.c
index 5eb7f30edc1f..db57345a9daf 100644
--- a/arch/parisc/kernel/kexec.c
+++ b/arch/parisc/kernel/kexec.c
@@ -4,6 +4,8 @@
 #include <linux/console.h>
 #include <linux/kexec.h>
 #include <linux/delay.h>
+#include <linux/reboot.h>
+
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
 
diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile
index 5d7cb991f2b8..7b593d44c712 100644
--- a/arch/riscv/kernel/pi/Makefile
+++ b/arch/riscv/kernel/pi/Makefile
@@ -22,7 +22,7 @@ KCOV_INSTRUMENT	:= n
 
 $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \
 			       --remove-section=.note.gnu.property \
-			       --prefix-alloc-sections=.init
+			       --prefix-alloc-sections=.init.pi
 $(obj)/%.pi.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index f03b5697f8e0..e5f9f4677bbf 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -84,11 +84,8 @@ SECTIONS
 	__init_data_begin = .;
 	INIT_DATA_SECTION(16)
 
-	/* Those sections result from the compilation of kernel/pi/string.c */
-	.init.pidata : {
-		*(.init.srodata.cst8*)
-		*(.init__bug_table*)
-		*(.init.sdata*)
+	.init.pi : {
+		*(.init.pi*)
 	}
 
 	.init.bss : {
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d096b04bf80e..9d248703cbdd 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1703,10 +1703,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event)) {
-			data.br_stack = &cpuc->lbr_stack;
-			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
-		}
+		if (has_branch_stack(event))
+			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index a2e566e53076..df88576d6b2a 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1229,12 +1229,14 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
 		  struct perf_event *event, bool add)
 {
 	struct pmu *pmu = event->pmu;
+
 	/*
 	 * Make sure we get updated with the first PEBS
 	 * event. It will trigger also during removal, but
 	 * that does not hurt:
 	 */
-	bool update = cpuc->n_pebs == 1;
+	if (cpuc->n_pebs == 1)
+		cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW;
 
 	if (needed_cb != pebs_needs_sched_cb(cpuc)) {
 		if (!needed_cb)
@@ -1242,7 +1244,7 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
 		else
 			perf_sched_cb_dec(pmu);
 
-		update = true;
+		cpuc->pebs_data_cfg |= PEBS_UPDATE_DS_SW;
 	}
 
 	/*
@@ -1252,24 +1254,13 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
 	if (x86_pmu.intel_cap.pebs_baseline && add) {
 		u64 pebs_data_cfg;
 
-		/* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
-		if (cpuc->n_pebs == 1) {
-			cpuc->pebs_data_cfg = 0;
-			cpuc->pebs_record_size = sizeof(struct pebs_basic);
-		}
-
 		pebs_data_cfg = pebs_update_adaptive_cfg(event);
-
-		/* Update pebs_record_size if new event requires more data. */
-		if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
-			cpuc->pebs_data_cfg |= pebs_data_cfg;
-			adaptive_pebs_record_size_update();
-			update = true;
-		}
+		/*
+		 * Be sure to update the thresholds when we change the record.
+		 */
+		if (pebs_data_cfg & ~cpuc->pebs_data_cfg)
+			cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW;
 	}
-
-	if (update)
-		pebs_update_threshold(cpuc);
 }
 
 void intel_pmu_pebs_add(struct perf_event *event)
@@ -1326,9 +1317,17 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
 	wrmsrl(base + idx, value);
 }
 
+static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc)
+{
+	if (cpuc->n_pebs == cpuc->n_large_pebs &&
+	    cpuc->n_pebs != cpuc->n_pebs_via_pt)
+		intel_pmu_drain_pebs_buffer();
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u64 pebs_data_cfg = cpuc->pebs_data_cfg & ~PEBS_UPDATE_DS_SW;
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
 	unsigned int idx = hwc->idx;
@@ -1344,11 +1343,22 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 	if (x86_pmu.intel_cap.pebs_baseline) {
 		hwc->config |= ICL_EVENTSEL_ADAPTIVE;
-		if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
-			wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
-			cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+		if (pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+			/*
+			 * drain_pebs() assumes uniform record size;
+			 * hence we need to drain when changing said
+			 * size.
+			 */
+			intel_pmu_drain_large_pebs(cpuc);
+			adaptive_pebs_record_size_update();
+			wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg);
+			cpuc->active_pebs_data_cfg = pebs_data_cfg;
 		}
 	}
+	if (cpuc->pebs_data_cfg & PEBS_UPDATE_DS_SW) {
+		cpuc->pebs_data_cfg = pebs_data_cfg;
+		pebs_update_threshold(cpuc);
+	}
 
 	if (idx >= INTEL_PMC_IDX_FIXED) {
 		if (x86_pmu.intel_cap.pebs_format < 5)
@@ -1391,9 +1401,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (cpuc->n_pebs == cpuc->n_large_pebs &&
-	    cpuc->n_pebs != cpuc->n_pebs_via_pt)
-		intel_pmu_drain_pebs_buffer();
+	intel_pmu_drain_large_pebs(cpuc);
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8fc15ed5e60b..abf09882f58b 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -121,6 +121,9 @@
 #define PEBS_DATACFG_LBRS	BIT_ULL(3)
 #define PEBS_DATACFG_LBR_SHIFT	24
 
+/* Steal the highest bit of pebs_data_cfg for SW usage */
+#define PEBS_UPDATE_DS_SW	BIT_ULL(63)
+
 /*
  * Intel "Architectural Performance Monitoring" CPUID
  * detection/enumeration details:
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 4266b64631a4..7e331e8f3692 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -36,6 +36,7 @@
 #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e
 #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4
 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4
+#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc
 
 /* Protect the PCI config register pairs used for SMN. */
 static DEFINE_MUTEX(smn_mutex);
@@ -79,6 +80,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) },
 	{}
 };
 
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 27ef53fab6bd..b3b1e376dce8 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -144,8 +144,8 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
  */
 	.align 64
 	.skip 63, 0xcc
-SYM_FUNC_START_NOALIGN(zen_untrain_ret);
-
+SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+	ANNOTATE_NOENDBR
 	/*
 	 * As executed from zen_untrain_ret, this is:
 	 *