Merge tag 'x86_urgent_for_v6.12_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - Explicitly disable the TSC deadline timer when going idle to address
   some CPU errata in that area

 - Do not apply the Zenbleed fix on anything else except AMD Zen2 on the
   late microcode loading path

 - Clear CPU buffers later in the NMI exit path on 32-bit to avoid
   register clearing while they still contain sensitive data, for the
   RDFS mitigation

 - Do not clobber EFLAGS.ZF with VERW on the opportunistic SYSRET exit
   path on 32-bit

 - Fix parsing issues of memory bandwidth specification in sysfs for
   resctrl's memory bandwidth allocation feature

 - Other small cleanups and improvements

* tag 'x86_urgent_for_v6.12_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/apic: Always explicitly disarm TSC-deadline timer
  x86/CPU/AMD: Only apply Zenbleed fix for Zen2 during late microcode load
  x86/bugs: Use code segment selector for VERW operand
  x86/entry_32: Clear CPU buffers after register restore in NMI return
  x86/entry_32: Do not clobber user EFLAGS.ZF
  x86/resctrl: Annotate get_mem_config() functions as __init
  x86/resctrl: Avoid overflow in MB settings in bw_validate()
  x86/amd_nb: Add new PCI ID for AMD family 1Ah model 20h

Author: torvalds

arch/x86/entry/entry_32.S

@@ -871,6 +871,8 @@ SYM_FUNC_START(entry_SYSENTER_32)
 
 	/* Now ready to switch the cr3 */
 	SWITCH_TO_USER_CR3 scratch_reg=%eax
+	/* Clobbers ZF */
+	CLEAR_CPU_BUFFERS
 
 	/*
 	 * Restore all flags except IF. (We restore IF separately because
@@ -881,7 +883,6 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	BUG_IF_WRONG_CR3 no_user_check=1
 	popfl
 	popl	%eax
-	CLEAR_CPU_BUFFERS
 
 	/*
 	 * Return back to the vDSO, which will pop ecx and edx.
@@ -1144,7 +1145,6 @@ SYM_CODE_START(asm_exc_nmi)
 
 	/* Not on SYSENTER stack. */
 	call	exc_nmi
-	CLEAR_CPU_BUFFERS
 	jmp	.Lnmi_return
 
 .Lnmi_from_sysenter_stack:
@@ -1165,6 +1165,7 @@ SYM_CODE_START(asm_exc_nmi)
 
 	CHECK_AND_APPLY_ESPFIX
 	RESTORE_ALL_NMI cr3_reg=%edi pop=4
+	CLEAR_CPU_BUFFERS
 	jmp	.Lirq_return
 
 #ifdef CONFIG_X86_ESPFIX32
@@ -1206,6 +1207,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 *  1 - orig_ax
 	 */
 	lss	(1+5+6)*4(%esp), %esp			# back to espfix stack
+	CLEAR_CPU_BUFFERS
 	jmp	.Lirq_return
 #endif
 SYM_CODE_END(asm_exc_nmi)

arch/x86/include/asm/nospec-branch.h

@@ -323,7 +323,16 @@
  * Note: Only the memory operand variant of VERW clears the CPU buffers.
  */
 .macro CLEAR_CPU_BUFFERS
-	ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
+#ifdef CONFIG_X86_64
+	ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
+#else
+	/*
+	 * In 32bit mode, the memory operand must be a %cs reference. The data
+	 * segments may not be usable (vm86 mode), and the stack segment may not
+	 * be flat (ESPFIX32).
+	 */
+	ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
+#endif
 .endm
 
 #ifdef CONFIG_X86_64

arch/x86/kernel/amd_nb.c

@@ -44,6 +44,7 @@
 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4	0x14f4
 #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4	0x12fc
 #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4	0x12c4
+#define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4	0x16fc
 #define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4	0x124c
 #define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4	0x12bc
 #define PCI_DEVICE_ID_AMD_MI200_DF_F4		0x14d4
@@ -127,6 +128,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) },

arch/x86/kernel/apic/apic.c

@@ -440,7 +440,19 @@ static int lapic_timer_shutdown(struct clock_event_device *evt)
 	v = apic_read(APIC_LVTT);
 	v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
 	apic_write(APIC_LVTT, v);
-	apic_write(APIC_TMICT, 0);
+
+	/*
+	 * Setting APIC_LVT_MASKED (above) should be enough to tell
+	 * the hardware that this timer will never fire. But AMD
+	 * erratum 411 and some Intel CPU behavior circa 2024 say
+	 * otherwise.  Time for belt and suspenders programming: mask
+	 * the timer _and_ zero the counter registers:
+	 */
+	if (v & APIC_LVT_TIMER_TSCDEADLINE)
+		wrmsrl(MSR_IA32_TSC_DEADLINE, 0);
+	else
+		apic_write(APIC_TMICT, 0);
+
 	return 0;
 }
 

arch/x86/kernel/cpu/amd.c

@@ -1202,5 +1202,6 @@ void amd_check_microcode(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		return;
 
-	on_each_cpu(zenbleed_check_cpu, NULL, 1);
+	if (cpu_feature_enabled(X86_FEATURE_ZEN2))
+		on_each_cpu(zenbleed_check_cpu, NULL, 1);
 }

arch/x86/kernel/cpu/resctrl/core.c

@@ -207,7 +207,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r)
 	return false;
 }
 
-static bool __get_mem_config_intel(struct rdt_resource *r)
+static __init bool __get_mem_config_intel(struct rdt_resource *r)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	union cpuid_0x10_3_eax eax;
@@ -241,7 +241,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 	return true;
 }
 
-static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
+static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	u32 eax, ebx, ecx, edx, subleaf;

arch/x86/kernel/cpu/resctrl/ctrlmondata.c

@@ -29,10 +29,10 @@
  * hardware. The allocated bandwidth percentage is rounded to the next
  * control step available on the hardware.
  */
-static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
-	unsigned long bw;
 	int ret;
+	u32 bw;
 
 	/*
 	 * Only linear delay values is supported for current Intel SKUs.
@@ -42,16 +42,21 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 		return false;
 	}
 
-	ret = kstrtoul(buf, 10, &bw);
+	ret = kstrtou32(buf, 10, &bw);
 	if (ret) {
-		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
+		rdt_last_cmd_printf("Invalid MB value %s\n", buf);
 		return false;
 	}
 
-	if ((bw < r->membw.min_bw || bw > r->default_ctrl) &&
-	    !is_mba_sc(r)) {
-		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
-				    r->membw.min_bw, r->default_ctrl);
+	/* Nothing else to do if software controller is enabled. */
+	if (is_mba_sc(r)) {
+		*data = bw;
+		return true;
+	}
+
+	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+		rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n",
+				    bw, r->membw.min_bw, r->default_ctrl);
 		return false;
 	}
 
@@ -65,7 +70,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
 	struct resctrl_staged_config *cfg;
 	u32 closid = data->rdtgrp->closid;
 	struct rdt_resource *r = s->res;
-	unsigned long bw_val;
+	u32 bw_val;
 
 	cfg = &d->staged_config[s->conf_type];
 	if (cfg->have_new_ctrl) {