Merge tag 'x86-urgent-2025-04-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull misc x86 fixes from Ingo Molnar:

 - Fix CPU topology related regression that limited Xen PV guests to a
   single CPU

 - Fix ancient e820__register_nosave_regions() bugs that were causing
   problems with kexec's artificial memory maps

 - Fix an S4 hibernation crash caused by two missing ENDBR's that were
   mistakenly removed in a recent commit

 - Fix a resctrl serialization bug

 - Fix early_printk documentation and comments

 - Fix RSB bugs, combined with preparatory updates to better match the
   code to vendor recommendations.

 - Add RSB mitigation document

 - Fix/update documentation

 - Fix the erratum_1386_microcode[] table to be NULL terminated

* tag 'x86-urgent-2025-04-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ibt: Fix hibernate
  x86/cpu: Avoid running off the end of an AMD erratum table
  Documentation/x86: Zap the subsection letters
  Documentation/x86: Update the naming of CPU features for /proc/cpuinfo
  x86/bugs: Add RSB mitigation document
  x86/bugs: Don't fill RSB on context switch with eIBRS
  x86/bugs: Don't fill RSB on VMEXIT with eIBRS+retpoline
  x86/bugs: Fix RSB clearing in indirect_branch_prediction_barrier()
  x86/bugs: Use SBPB in write_ibpb() if applicable
  x86/bugs: Rename entry_ibpb() to write_ibpb()
  x86/early_printk: Use 'mmio32' for consistency, fix comments
  x86/resctrl: Fix rdtgroup_mkdir()'s unlocked use of kernfs_node::name
  x86/e820: Fix handling of subpage regions when calculating nosave ranges in e820__register_nosave_regions()
  x86/acpi: Don't limit CPUs to 1 for Xen PV guests due to disabled ACPI

1 files changed, 31 insertions, 70 deletions

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4386aa6c69e1..362602b705cc 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -59,7 +59,6 @@ DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
 EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current);
 
 u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
-EXPORT_SYMBOL_GPL(x86_pred_cmd);
 
 static u64 __ro_after_init x86_arch_cap_msr;
 
@@ -1142,7 +1141,7 @@ do_cmd_auto:
 		setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
 
 		/*
-		 * There is no need for RSB filling: entry_ibpb() ensures
+		 * There is no need for RSB filling: write_ibpb() ensures
 		 * all predictions, including the RSB, are invalidated,
 		 * regardless of IBPB implementation.
 		 */
@@ -1592,51 +1591,54 @@ static void __init spec_ctrl_disable_kernel_rrsba(void)
 	rrsba_disabled = true;
 }
 
-static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode)
+static void __init spectre_v2_select_rsb_mitigation(enum spectre_v2_mitigation mode)
 {
 	/*
-	 * Similar to context switches, there are two types of RSB attacks
-	 * after VM exit:
+	 * WARNING! There are many subtleties to consider when changing *any*
+	 * code related to RSB-related mitigations.  Before doing so, carefully
+	 * read the following document, and update if necessary:
 	 *
-	 * 1) RSB underflow
+	 *   Documentation/admin-guide/hw-vuln/rsb.rst
 	 *
-	 * 2) Poisoned RSB entry
+	 * In an overly simplified nutshell:
 	 *
-	 * When retpoline is enabled, both are mitigated by filling/clearing
-	 * the RSB.
+	 *   - User->user RSB attacks are conditionally mitigated during
+	 *     context switches by cond_mitigation -> write_ibpb().
 	 *
-	 * When IBRS is enabled, while #1 would be mitigated by the IBRS branch
-	 * prediction isolation protections, RSB still needs to be cleared
-	 * because of #2.  Note that SMEP provides no protection here, unlike
-	 * user-space-poisoned RSB entries.
+	 *   - User->kernel and guest->host attacks are mitigated by eIBRS or
+	 *     RSB filling.
 	 *
-	 * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB
-	 * bug is present then a LITE version of RSB protection is required,
-	 * just a single call needs to retire before a RET is executed.
+	 *     Though, depending on config, note that other alternative
+	 *     mitigations may end up getting used instead, e.g., IBPB on
+	 *     entry/vmexit, call depth tracking, or return thunks.
 	 */
+
 	switch (mode) {
 	case SPECTRE_V2_NONE:
-		return;
+		break;
 
-	case SPECTRE_V2_EIBRS_LFENCE:
 	case SPECTRE_V2_EIBRS:
+	case SPECTRE_V2_EIBRS_LFENCE:
+	case SPECTRE_V2_EIBRS_RETPOLINE:
 		if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
-			setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
 			pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n");
+			setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
 		}
-		return;
+		break;
 
-	case SPECTRE_V2_EIBRS_RETPOLINE:
 	case SPECTRE_V2_RETPOLINE:
 	case SPECTRE_V2_LFENCE:
 	case SPECTRE_V2_IBRS:
+		pr_info("Spectre v2 / SpectreRSB: Filling RSB on context switch and VMEXIT\n");
+		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
 		setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT);
-		pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n");
-		return;
-	}
+		break;
 
-	pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit");
-	dump_stack();
+	default:
+		pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation\n");
+		dump_stack();
+		break;
+	}
 }
 
 /*
@@ -1830,48 +1832,7 @@ static void __init spectre_v2_select_mitigation(void)
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
-	/*
-	 * If Spectre v2 protection has been enabled, fill the RSB during a
-	 * context switch.  In general there are two types of RSB attacks
-	 * across context switches, for which the CALLs/RETs may be unbalanced.
-	 *
-	 * 1) RSB underflow
-	 *
-	 *    Some Intel parts have "bottomless RSB".  When the RSB is empty,
-	 *    speculated return targets may come from the branch predictor,
-	 *    which could have a user-poisoned BTB or BHB entry.
-	 *
-	 *    AMD has it even worse: *all* returns are speculated from the BTB,
-	 *    regardless of the state of the RSB.
-	 *
-	 *    When IBRS or eIBRS is enabled, the "user -> kernel" attack
-	 *    scenario is mitigated by the IBRS branch prediction isolation
-	 *    properties, so the RSB buffer filling wouldn't be necessary to
-	 *    protect against this type of attack.
-	 *
-	 *    The "user -> user" attack scenario is mitigated by RSB filling.
-	 *
-	 * 2) Poisoned RSB entry
-	 *
-	 *    If the 'next' in-kernel return stack is shorter than 'prev',
-	 *    'next' could be tricked into speculating with a user-poisoned RSB
-	 *    entry.
-	 *
-	 *    The "user -> kernel" attack scenario is mitigated by SMEP and
-	 *    eIBRS.
-	 *
-	 *    The "user -> user" scenario, also known as SpectreBHB, requires
-	 *    RSB clearing.
-	 *
-	 * So to mitigate all cases, unconditionally fill RSB on context
-	 * switches.
-	 *
-	 * FIXME: Is this pointless for retbleed-affected AMD?
-	 */
-	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
-
-	spectre_v2_determine_rsb_fill_type_at_vmexit(mode);
+	spectre_v2_select_rsb_mitigation(mode);
 
 	/*
 	 * Retpoline protects the kernel, but doesn't protect firmware.  IBRS
@@ -2676,7 +2637,7 @@ static void __init srso_select_mitigation(void)
 				setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
 
 				/*
-				 * There is no need for RSB filling: entry_ibpb() ensures
+				 * There is no need for RSB filling: write_ibpb() ensures
 				 * all predictions, including the RSB, are invalidated,
 				 * regardless of IBPB implementation.
 				 */
@@ -2701,7 +2662,7 @@ ibpb_on_vmexit:
 				srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
 
 				/*
-				 * There is no need for RSB filling: entry_ibpb() ensures
+				 * There is no need for RSB filling: write_ibpb() ensures
 				 * all predictions, including the RSB, are invalidated,
 				 * regardless of IBPB implementation.
 				 */