Merge tag 'v6.2-rc4' into perf/core, to pick up fixes

Move from the -rc1 base to the fresher -rc4 kernel that
has various fixes included, before applying a larger
patchset.

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

8 files changed, 73 insertions, 54 deletions

diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 7d2c75ec9a8c..ffea98f9064b 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -119,7 +119,7 @@ static bool is_coretext(const struct core_text *ct, void *addr)
 	return within_module_coretext(addr);
 }
 
-static __init_or_module bool skip_addr(void *dest)
+static bool skip_addr(void *dest)
 {
 	if (dest == error_entry)
 		return true;
@@ -181,7 +181,7 @@ static const u8 nops[] = {
 	0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
 };
 
-static __init_or_module void *patch_dest(void *dest, bool direct)
+static void *patch_dest(void *dest, bool direct)
 {
 	unsigned int tsize = SKL_TMPL_SIZE;
 	u8 *pad = dest - tsize;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d970ddb0cc65..bca0bd8f4846 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1981,6 +1981,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);
 		task_update_spec_tif(task);
+		if (task == current)
+			indirect_branch_prediction_barrier();
 		break;
 	default:
 		return -ERANGE;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index efe0c30d3a12..77538abeb72a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 	return entry;
 }
 
+static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+	u64 msr_val;
+
+	/*
+	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+	 * with a valid event code for supported resource type and the bits
+	 * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+	 * are error bits.
+	 */
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	*val = msr_val;
+	return 0;
+}
+
 static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
@@ -172,8 +196,12 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
 	struct arch_mbm_state *am;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
-	if (am)
+	if (am) {
 		memset(am, 0, sizeof(*am));
+
+		/* Record any initial, non-zero count value. */
+		__rmid_read(rmid, eventid, &am->prev_msr);
+	}
 }
 
 static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
@@ -191,25 +219,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
+	int ret;
 
 	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
 		return -EINVAL;
 
-	/*
-	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
-	 * with a valid event code for supported resource type and the bits
-	 * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
-	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
-	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
-	 * are error bits.
-	 */
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
-	rdmsrl(MSR_IA32_QM_CTR, msr_val);
-
-	if (msr_val & RMID_VAL_ERROR)
-		return -EIO;
-	if (msr_val & RMID_VAL_UNAVAIL)
-		return -EINVAL;
+	ret = __rmid_read(rmid, eventid, &msr_val);
+	if (ret)
+		return ret;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
 	if (am) {
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index e5a48f05e787..5993da21d822 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -580,8 +580,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	/*
 	 * Ensure the task's closid and rmid are written before determining if
 	 * the task is current that will decide if it will be interrupted.
+	 * This pairs with the full barrier between the rq->curr update and
+	 * resctrl_sched_in() during context switch.
 	 */
-	barrier();
+	smp_mb();
 
 	/*
 	 * By now, the task's closid and rmid are set. If the task is current
@@ -2402,6 +2404,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 			WRITE_ONCE(t->rmid, to->mon.rmid);
 
 			/*
+			 * Order the closid/rmid stores above before the loads
+			 * in task_curr(). This pairs with the full barrier
+			 * between the rq->curr update and resctrl_sched_in()
+			 * during context switch.
+			 */
+			smp_mb();
+
+			/*
 			 * If the task is on a CPU, set the CPU in the mask.
 			 * The detection is inaccurate as tasks might move or
 			 * schedule before the smp function call takes place.
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 9730c88530fc..305514431f26 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -401,10 +401,8 @@ int crash_load_segments(struct kimage *image)
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
-	if (ret) {
-		vfree((void *)image->elf_headers);
+	if (ret)
 		return ret;
-	}
 	image->elf_load_addr = kbuf.mem;
 	pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
 		 image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fd0420a3e72e..cd529aed2e7b 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -37,6 +37,7 @@
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/kasan.h>
 #include <linux/moduleloader.h>
@@ -281,12 +282,15 @@ static int can_probe(unsigned long paddr)
 		if (ret < 0)
 			return 0;
 
+#ifdef CONFIG_KGDB
 		/*
-		 * Another debugging subsystem might insert this breakpoint.
-		 * In that case, we can't recover it.
+		 * If there is a dynamically installed kgdb sw breakpoint,
+		 * this function should not be probed.
 		 */
-		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+		    kgdb_has_hit_break(addr))
 			return 0;
+#endif
 		addr += insn.length;
 	}
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index e6b8c5362b94..e57e07b0edb6 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -15,6 +15,7 @@
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/objtool.h>
 #include <linux/pgtable.h>
@@ -279,19 +280,6 @@ static int insn_is_indirect_jump(struct insn *insn)
 	return ret;
 }
 
-static bool is_padding_int3(unsigned long addr, unsigned long eaddr)
-{
-	unsigned char ops;
-
-	for (; addr < eaddr; addr++) {
-		if (get_kernel_nofault(ops, (void *)addr) < 0 ||
-		    ops != INT3_INSN_OPCODE)
-			return false;
-	}
-
-	return true;
-}
-
 /* Decode whole function to ensure any instructions don't jump into target */
 static int can_optimize(unsigned long paddr)
 {
@@ -334,15 +322,15 @@ static int can_optimize(unsigned long paddr)
 		ret = insn_decode_kernel(&insn, (void *)recovered_insn);
 		if (ret < 0)
 			return 0;
-
+#ifdef CONFIG_KGDB
 		/*
-		 * In the case of detecting unknown breakpoint, this could be
-		 * a padding INT3 between functions. Let's check that all the
-		 * rest of the bytes are also INT3.
+		 * If there is a dynamically installed kgdb sw breakpoint,
+		 * this function should not be probed.
 		 */
-		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
-			return is_padding_int3(addr, paddr - offset + size) ? 1 : 0;
-
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+		    kgdb_has_hit_break(addr))
+			return 0;
+#endif
 		/* Recover address */
 		insn.kaddr = (void *)addr;
 		insn.next_byte = (void *)(addr + insn.length);
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index a428c62330d3..679026a640ef 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -1536,32 +1536,32 @@ static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
 static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 {
 	struct insn *insn = &ctxt->insn;
+	enum insn_mmio_type mmio;
 	unsigned int bytes = 0;
-	enum mmio_type mmio;
 	enum es_result ret;
 	u8 sign_byte;
 	long *reg_data;
 
 	mmio = insn_decode_mmio(insn, &bytes);
-	if (mmio == MMIO_DECODE_FAILED)
+	if (mmio == INSN_MMIO_DECODE_FAILED)
 		return ES_DECODE_FAILED;
 
-	if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
 		reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
 		if (!reg_data)
 			return ES_DECODE_FAILED;
 	}
 
 	switch (mmio) {
-	case MMIO_WRITE:
+	case INSN_MMIO_WRITE:
 		memcpy(ghcb->shared_buffer, reg_data, bytes);
 		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
 		break;
-	case MMIO_WRITE_IMM:
+	case INSN_MMIO_WRITE_IMM:
 		memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
 		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
 		break;
-	case MMIO_READ:
+	case INSN_MMIO_READ:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
@@ -1572,7 +1572,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_READ_ZERO_EXTEND:
+	case INSN_MMIO_READ_ZERO_EXTEND:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
@@ -1581,7 +1581,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 		memset(reg_data, 0, insn->opnd_bytes);
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_READ_SIGN_EXTEND:
+	case INSN_MMIO_READ_SIGN_EXTEND:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
@@ -1600,7 +1600,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 		memset(reg_data, sign_byte, insn->opnd_bytes);
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_MOVS:
+	case INSN_MMIO_MOVS:
 		ret = vc_handle_mmio_movs(ctxt, bytes);
 		break;
 	default: