Merge tag 'x86-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core x86 updates from Ingo Molnar:
 "x86 CPU features support:
   - Generate the <asm/cpufeaturemasks.h> header based on build config
     (H. Peter Anvin, Xin Li)
   - x86 CPUID parsing updates and fixes (Ahmed S. Darwish)
   - Introduce the 'setcpuid=' boot parameter (Brendan Jackman)
   - Enable modifying CPU bug flags with '{clear,set}puid=' (Brendan
     Jackman)
   - Utilize CPU-type for CPU matching (Pawan Gupta)
   - Warn about unmet CPU feature dependencies (Sohil Mehta)
   - Prepare for new Intel Family numbers (Sohil Mehta)

  Percpu code:
   - Standardize & reorganize the x86 percpu layout and related cleanups
     (Brian Gerst)
   - Convert the stackprotector canary to a regular percpu variable
     (Brian Gerst)
   - Add a percpu subsection for cache hot data (Brian Gerst)
   - Unify __pcpu_op{1,2}_N() macros to __pcpu_op_N() (Uros Bizjak)
   - Construct __percpu_seg_override from __percpu_seg (Uros Bizjak)

  MM:
   - Add support for broadcast TLB invalidation using AMD's INVLPGB
     instruction (Rik van Riel)
   - Rework ROX cache to avoid writable copy (Mike Rapoport)
   - PAT: restore large ROX pages after fragmentation (Kirill A.
     Shutemov, Mike Rapoport)
   - Make memremap(MEMREMAP_WB) map memory as encrypted by default
     (Kirill A. Shutemov)
   - Robustify page table initialization (Kirill A. Shutemov)
   - Fix flush_tlb_range() when used for zapping normal PMDs (Jann Horn)
   - Clear _PAGE_DIRTY for kernel mappings when we clear _PAGE_RW
     (Matthew Wilcox)

  KASLR:
   - x86/kaslr: Reduce KASLR entropy on most x86 systems, to support PCI
     BAR space beyond the 10TiB region (CONFIG_PCI_P2PDMA=y) (Balbir
     Singh)

  CPU bugs:
   - Implement FineIBT-BHI mitigation (Peter Zijlstra)
   - speculation: Simplify and make CALL_NOSPEC consistent (Pawan Gupta)
   - speculation: Add a conditional CS prefix to CALL_NOSPEC (Pawan
     Gupta)
   - RFDS: Exclude P-only parts from the RFDS affected list (Pawan
     Gupta)

  System calls:
   - Break up entry/common.c (Brian Gerst)
   - Move sysctls into arch/x86 (Joel Granados)

  Intel LAM support updates: (Maciej Wieczor-Retman)
   - selftests/lam: Move cpu_has_la57() to use cpuinfo flag
   - selftests/lam: Skip test if LAM is disabled
   - selftests/lam: Test get_user() LAM pointer handling

  AMD SMN access updates:
   - Add SMN offsets to exclusive region access (Mario Limonciello)
   - Add support for debugfs access to SMN registers (Mario Limonciello)
   - Have HSMP use SMN through AMD_NODE (Yazen Ghannam)

  Power management updates: (Patryk Wlazlyn)
   - Allow calling mwait_play_dead with an arbitrary hint
   - ACPI/processor_idle: Add FFH state handling
   - intel_idle: Provide the default enter_dead() handler
   - Eliminate mwait_play_dead_cpuid_hint()

  Build system:
   - Raise the minimum GCC version to 8.1 (Brian Gerst)
   - Raise the minimum LLVM version to 15.0.0 (Nathan Chancellor)

  Kconfig: (Arnd Bergmann)
   - Add cmpxchg8b support back to Geode CPUs
   - Drop 32-bit "bigsmp" machine support
   - Rework CONFIG_GENERIC_CPU compiler flags
   - Drop configuration options for early 64-bit CPUs
   - Remove CONFIG_HIGHMEM64G support
   - Drop CONFIG_SWIOTLB for PAE
   - Drop support for CONFIG_HIGHPTE
   - Document CONFIG_X86_INTEL_MID as 64-bit-only
   - Remove old STA2x11 support
   - Only allow CONFIG_EISA for 32-bit

  Headers:
   - Replace __ASSEMBLY__ with __ASSEMBLER__ in UAPI and non-UAPI
     headers (Thomas Huth)

  Assembly code & machine code patching:
   - x86/alternatives: Simplify alternative_call() interface (Josh
     Poimboeuf)
   - x86/alternatives: Simplify callthunk patching (Peter Zijlstra)
   - KVM: VMX: Use named operands in inline asm (Josh Poimboeuf)
   - x86/hyperv: Use named operands in inline asm (Josh Poimboeuf)
   - x86/traps: Cleanup and robustify decode_bug() (Peter Zijlstra)
   - x86/kexec: Merge x86_32 and x86_64 code using macros from
     <asm/asm.h> (Uros Bizjak)
   - Use named operands in inline asm (Uros Bizjak)
   - Improve performance by using asm_inline() for atomic locking
     instructions (Uros Bizjak)

  Earlyprintk:
   - Harden early_serial (Peter Zijlstra)

  NMI handler:
   - Add an emergency handler in nmi_desc & use it in
     nmi_shootdown_cpus() (Waiman Long)

  Miscellaneous fixes and cleanups:
   - by Ahmed S. Darwish, Andy Shevchenko, Ard Biesheuvel, Artem
     Bityutskiy, Borislav Petkov, Brendan Jackman, Brian Gerst, Dan
     Carpenter, Dr. David Alan Gilbert, H. Peter Anvin, Ingo Molnar,
     Josh Poimboeuf, Kevin Brodsky, Mike Rapoport, Lukas Bulwahn, Maciej
     Wieczor-Retman, Max Grobecker, Patryk Wlazlyn, Pawan Gupta, Peter
     Zijlstra, Philip Redkin, Qasim Ijaz, Rik van Riel, Thomas Gleixner,
     Thorsten Blum, Tom Lendacky, Tony Luck, Uros Bizjak, Vitaly
     Kuznetsov, Xin Li, liuye"

* tag 'x86-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (211 commits)
  zstd: Increase DYNAMIC_BMI2 GCC version cutoff from 4.8 to 11.0 to work around compiler segfault
  x86/asm: Make asm export of __ref_stack_chk_guard unconditional
  x86/mm: Only do broadcast flush from reclaim if pages were unmapped
  perf/x86/intel, x86/cpu: Replace Pentium 4 model checks with VFM ones
  perf/x86/intel, x86/cpu: Simplify Intel PMU initialization
  x86/headers: Replace __ASSEMBLY__ with __ASSEMBLER__ in non-UAPI headers
  x86/headers: Replace __ASSEMBLY__ with __ASSEMBLER__ in UAPI headers
  x86/locking/atomic: Improve performance by using asm_inline() for atomic locking instructions
  x86/asm: Use asm_inline() instead of asm() in clwb()
  x86/asm: Use CLFLUSHOPT and CLWB mnemonics in <asm/special_insns.h>
  x86/hweight: Use asm_inline() instead of asm()
  x86/hweight: Use ASM_CALL_CONSTRAINT in inline asm()
  x86/hweight: Use named operands in inline asm()
  x86/stackprotector/64: Only export __ref_stack_chk_guard on CONFIG_SMP
  x86/head/64: Avoid Clang < 17 stack protector in startup code
  x86/kexec: Merge x86_32 and x86_64 code using macros from <asm/asm.h>
  x86/runtime-const: Add the RUNTIME_CONST_PTR assembly macro
  x86/cpu/intel: Limit the non-architectural constant_tsc model checks
  x86/mm/pat: Replace Intel x86_model checks with VFM ones
  x86/cpu/intel: Fix fast string initialization for extended Families
  ...

1 files changed, 391 insertions, 38 deletions

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6cf881a942bb..0925768d00cb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -74,13 +74,15 @@
  * use different names for each of them:
  *
  * ASID  - [0, TLB_NR_DYN_ASIDS-1]
- *         the canonical identifier for an mm
+ *         the canonical identifier for an mm, dynamically allocated on each CPU
+ *         [TLB_NR_DYN_ASIDS, MAX_ASID_AVAILABLE-1]
+ *         the canonical, global identifier for an mm, identical across all CPUs
  *
- * kPCID - [1, TLB_NR_DYN_ASIDS]
+ * kPCID - [1, MAX_ASID_AVAILABLE]
  *         the value we write into the PCID part of CR3; corresponds to the
  *         ASID+1, because PCID 0 is special.
  *
- * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ * uPCID - [2048 + 1, 2048 + MAX_ASID_AVAILABLE]
  *         for KPTI each mm has two address spaces and thus needs two
  *         PCID values, but we can still do with a single ASID denomination
  *         for each mm. Corresponds to kPCID + 2048.
@@ -225,6 +227,20 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 		return;
 	}
 
+	/*
+	 * TLB consistency for global ASIDs is maintained with hardware assisted
+	 * remote TLB flushing. Global ASIDs are always up to date.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		u16 global_asid = mm_global_asid(next);
+
+		if (global_asid) {
+			*new_asid = global_asid;
+			*need_flush = false;
+			return;
+		}
+	}
+
 	if (this_cpu_read(cpu_tlbstate.invalidate_other))
 		clear_asid_other();
 
@@ -252,6 +268,268 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 }
 
 /*
+ * Global ASIDs are allocated for multi-threaded processes that are
+ * active on multiple CPUs simultaneously, giving each of those
+ * processes the same PCID on every CPU, for use with hardware-assisted
+ * TLB shootdown on remote CPUs, like AMD INVLPGB or Intel RAR.
+ *
+ * These global ASIDs are held for the lifetime of the process.
+ */
+static DEFINE_RAW_SPINLOCK(global_asid_lock);
+static u16 last_global_asid = MAX_ASID_AVAILABLE;
+static DECLARE_BITMAP(global_asid_used, MAX_ASID_AVAILABLE);
+static DECLARE_BITMAP(global_asid_freed, MAX_ASID_AVAILABLE);
+static int global_asid_available = MAX_ASID_AVAILABLE - TLB_NR_DYN_ASIDS - 1;
+
+/*
+ * When the search for a free ASID in the global ASID space reaches
+ * MAX_ASID_AVAILABLE, a global TLB flush guarantees that previously
+ * freed global ASIDs are safe to re-use.
+ *
+ * This way the global flush only needs to happen at ASID rollover
+ * time, and not at ASID allocation time.
+ */
+static void reset_global_asid_space(void)
+{
+	lockdep_assert_held(&global_asid_lock);
+
+	invlpgb_flush_all_nonglobals();
+
+	/*
+	 * The TLB flush above makes it safe to re-use the previously
+	 * freed global ASIDs.
+	 */
+	bitmap_andnot(global_asid_used, global_asid_used,
+			global_asid_freed, MAX_ASID_AVAILABLE);
+	bitmap_clear(global_asid_freed, 0, MAX_ASID_AVAILABLE);
+
+	/* Restart the search from the start of global ASID space. */
+	last_global_asid = TLB_NR_DYN_ASIDS;
+}
+
+static u16 allocate_global_asid(void)
+{
+	u16 asid;
+
+	lockdep_assert_held(&global_asid_lock);
+
+	/* The previous allocation hit the edge of available address space */
+	if (last_global_asid >= MAX_ASID_AVAILABLE - 1)
+		reset_global_asid_space();
+
+	asid = find_next_zero_bit(global_asid_used, MAX_ASID_AVAILABLE, last_global_asid);
+
+	if (asid >= MAX_ASID_AVAILABLE && !global_asid_available) {
+		/* This should never happen. */
+		VM_WARN_ONCE(1, "Unable to allocate global ASID despite %d available\n",
+				global_asid_available);
+		return 0;
+	}
+
+	/* Claim this global ASID. */
+	__set_bit(asid, global_asid_used);
+	last_global_asid = asid;
+	global_asid_available--;
+	return asid;
+}
+
+/*
+ * Check whether a process is currently active on more than @threshold CPUs.
+ * This is a cheap estimation on whether or not it may make sense to assign
+ * a global ASID to this process, and use broadcast TLB invalidation.
+ */
+static bool mm_active_cpus_exceeds(struct mm_struct *mm, int threshold)
+{
+	int count = 0;
+	int cpu;
+
+	/* This quick check should eliminate most single threaded programs. */
+	if (cpumask_weight(mm_cpumask(mm)) <= threshold)
+		return false;
+
+	/* Slower check to make sure. */
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/* Skip the CPUs that aren't really running this process. */
+		if (per_cpu(cpu_tlbstate.loaded_mm, cpu) != mm)
+			continue;
+
+		if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+			continue;
+
+		if (++count > threshold)
+			return true;
+	}
+	return false;
+}
+
+/*
+ * Assign a global ASID to the current process, protecting against
+ * races between multiple threads in the process.
+ */
+static void use_global_asid(struct mm_struct *mm)
+{
+	u16 asid;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* This process is already using broadcast TLB invalidation. */
+	if (mm_global_asid(mm))
+		return;
+
+	/*
+	 * The last global ASID was consumed while waiting for the lock.
+	 *
+	 * If this fires, a more aggressive ASID reuse scheme might be
+	 * needed.
+	 */
+	if (!global_asid_available) {
+		VM_WARN_ONCE(1, "Ran out of global ASIDs\n");
+		return;
+	}
+
+	asid = allocate_global_asid();
+	if (!asid)
+		return;
+
+	mm_assign_global_asid(mm, asid);
+}
+
+void mm_free_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	if (!mm_global_asid(mm))
+		return;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* The global ASID can be re-used only after flush at wrap-around. */
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+	__set_bit(mm->context.global_asid, global_asid_freed);
+
+	mm->context.global_asid = 0;
+	global_asid_available++;
+#endif
+}
+
+/*
+ * Is the mm transitioning from a CPU-local ASID to a global ASID?
+ */
+static bool mm_needs_global_asid(struct mm_struct *mm, u16 asid)
+{
+	u16 global_asid = mm_global_asid(mm);
+
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return false;
+
+	/* Process is transitioning to a global ASID */
+	if (global_asid && asid != global_asid)
+		return true;
+
+	return false;
+}
+
+/*
+ * x86 has 4k ASIDs (2k when compiled with KPTI), but the largest x86
+ * systems have over 8k CPUs. Because of this potential ASID shortage,
+ * global ASIDs are handed out to processes that have frequent TLB
+ * flushes and are active on 4 or more CPUs simultaneously.
+ */
+static void consider_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	/* Check every once in a while. */
+	if ((current->pid & 0x1f) != (jiffies & 0x1f))
+		return;
+
+	/*
+	 * Assign a global ASID if the process is active on
+	 * 4 or more CPUs simultaneously.
+	 */
+	if (mm_active_cpus_exceeds(mm, 3))
+		use_global_asid(mm);
+}
+
+static void finish_asid_transition(struct flush_tlb_info *info)
+{
+	struct mm_struct *mm = info->mm;
+	int bc_asid = mm_global_asid(mm);
+	int cpu;
+
+	if (!mm_in_asid_transition(mm))
+		return;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/*
+		 * The remote CPU is context switching. Wait for that to
+		 * finish, to catch the unlikely case of it switching to
+		 * the target mm with an out of date ASID.
+		 */
+		while (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) == LOADED_MM_SWITCHING)
+			cpu_relax();
+
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) != mm)
+			continue;
+
+		/*
+		 * If at least one CPU is not using the global ASID yet,
+		 * send a TLB flush IPI. The IPI should cause stragglers
+		 * to transition soon.
+		 *
+		 * This can race with the CPU switching to another task;
+		 * that results in a (harmless) extra IPI.
+		 */
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm_asid, cpu)) != bc_asid) {
+			flush_tlb_multi(mm_cpumask(info->mm), info);
+			return;
+		}
+	}
+
+	/* All the CPUs running this process are using the global ASID. */
+	mm_clear_asid_transition(mm);
+}
+
+static void broadcast_tlb_flush(struct flush_tlb_info *info)
+{
+	bool pmd = info->stride_shift == PMD_SHIFT;
+	unsigned long asid = mm_global_asid(info->mm);
+	unsigned long addr = info->start;
+
+	/*
+	 * TLB flushes with INVLPGB are kicked off asynchronously.
+	 * The inc_mm_tlb_gen() guarantees page table updates are done
+	 * before these TLB flushes happen.
+	 */
+	if (info->end == TLB_FLUSH_ALL) {
+		invlpgb_flush_single_pcid_nosync(kern_pcid(asid));
+		/* Do any CPUs supporting INVLPGB need PTI? */
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_single_pcid_nosync(user_pcid(asid));
+	} else do {
+		unsigned long nr = 1;
+
+		if (info->stride_shift <= PMD_SHIFT) {
+			nr = (info->end - addr) >> info->stride_shift;
+			nr = clamp_val(nr, 1, invlpgb_count_max);
+		}
+
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);
+
+		addr += nr << info->stride_shift;
+	} while (addr < info->end);
+
+	finish_asid_transition(info);
+
+	/* Wait for the INVLPGBs kicked off above to finish. */
+	__tlbsync();
+}
+
+/*
  * Given an ASID, flush the corresponding user ASID.  We can delay this
  * until the next time we switch to it.
  *
@@ -556,7 +834,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	 */
 	if (prev == next) {
 		/* Not actually switching mm's */
-		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+		VM_WARN_ON(is_dyn_asid(prev_asid) &&
+			   this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
 			   next->context.ctx_id);
 
 		/*
@@ -573,6 +852,20 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
+		/* Check if the current mm is transitioning to a global ASID */
+		if (mm_needs_global_asid(next, prev_asid)) {
+			next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+			choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+			goto reload_tlb;
+		}
+
+		/*
+		 * Broadcast TLB invalidation keeps this ASID up to date
+		 * all the time.
+		 */
+		if (is_global_asid(prev_asid))
+			return;
+
 		/*
 		 * If the CPU is not in lazy TLB mode, we are just switching
 		 * from one thread in a process to another thread in the same
@@ -607,6 +900,13 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		cond_mitigation(tsk);
 
 		/*
+		 * Let nmi_uaccess_okay() and finish_asid_transition()
+		 * know that CR3 is changing.
+		 */
+		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
+		barrier();
+
+		/*
 		 * Leave this CPU in prev's mm_cpumask. Atomic writes to
 		 * mm_cpumask can be expensive under contention. The CPU
 		 * will be removed lazily at TLB flush time.
@@ -620,14 +920,12 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
-
-		/* Let nmi_uaccess_okay() know that we're changing CR3. */
-		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
-		barrier();
 	}
 
+reload_tlb:
 	new_lam = mm_lam_cr3_mask(next);
 	if (need_flush) {
+		VM_WARN_ON_ONCE(is_global_asid(new_asid));
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
 		load_new_mm_cr3(next->pgd, new_asid, new_lam, true);
@@ -746,7 +1044,7 @@ static void flush_tlb_func(void *info)
 	const struct flush_tlb_info *f = info;
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
-	u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+	u64 local_tlb_gen;
 	bool local = smp_processor_id() == f->initiating_cpu;
 	unsigned long nr_invalidate = 0;
 	u64 mm_tlb_gen;
@@ -769,6 +1067,16 @@ static void flush_tlb_func(void *info)
 	if (unlikely(loaded_mm == &init_mm))
 		return;
 
+	/* Reload the ASID if transitioning into or out of a global ASID */
+	if (mm_needs_global_asid(loaded_mm, loaded_mm_asid)) {
+		switch_mm_irqs_off(NULL, loaded_mm, NULL);
+		loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	}
+
+	/* Broadcast ASIDs are always kept up to date with INVLPGB. */
+	if (is_global_asid(loaded_mm_asid))
+		return;
+
 	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
 		   loaded_mm->context.ctx_id);
 
@@ -786,6 +1094,8 @@ static void flush_tlb_func(void *info)
 		return;
 	}
 
+	local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+
 	if (unlikely(f->new_tlb_gen != TLB_GENERATION_INVALID &&
 		     f->new_tlb_gen <= local_tlb_gen)) {
 		/*
@@ -953,7 +1263,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	 * up on the new contents of what used to be page tables, while
 	 * doing a speculative memory access.
 	 */
-	if (info->freed_tables)
+	if (info->freed_tables || mm_in_asid_transition(info->mm))
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
 	else
 		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
@@ -1000,6 +1310,15 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
 	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
 #endif
 
+	/*
+	 * If the number of flushes is so large that a full flush
+	 * would be faster, do a full flush.
+	 */
+	if ((end - start) >> stride_shift > tlb_single_page_flush_ceiling) {
+		start = 0;
+		end = TLB_FLUSH_ALL;
+	}
+
 	info->start		= start;
 	info->end		= end;
 	info->mm		= mm;
@@ -1026,17 +1345,8 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				bool freed_tables)
 {
 	struct flush_tlb_info *info;
+	int cpu = get_cpu();
 	u64 new_tlb_gen;
-	int cpu;
-
-	cpu = get_cpu();
-
-	/* Should we flush just the requested range? */
-	if ((end == TLB_FLUSH_ALL) ||
-	    ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) {
-		start = 0;
-		end = TLB_FLUSH_ALL;
-	}
 
 	/* This is also a barrier that synchronizes with switch_mm(). */
 	new_tlb_gen = inc_mm_tlb_gen(mm);
@@ -1049,9 +1359,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+	if (mm_global_asid(mm)) {
+		broadcast_tlb_flush(info);
+	} else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
 		info->trim_cpumask = should_trim_cpumask(mm);
 		flush_tlb_multi(mm_cpumask(mm), info);
+		consider_global_asid(mm);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
@@ -1064,7 +1377,6 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
-
 static void do_flush_tlb_all(void *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -1074,7 +1386,32 @@ static void do_flush_tlb_all(void *info)
 void flush_tlb_all(void)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
-	on_each_cpu(do_flush_tlb_all, NULL, 1);
+
+	/* First try (faster) hardware-assisted TLB invalidation. */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
+		/* Fall back to the IPI-based invalidation. */
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+}
+
+/* Flush an arbitrarily large range of memory with INVLPGB. */
+static void invlpgb_kernel_range_flush(struct flush_tlb_info *info)
+{
+	unsigned long addr, nr;
+
+	for (addr = info->start; addr < info->end; addr += nr << PAGE_SHIFT) {
+		nr = (info->end - addr) >> PAGE_SHIFT;
+
+		/*
+		 * INVLPGB has a limit on the size of ranges it can
+		 * flush. Break up large flushes.
+		 */
+		nr = clamp_val(nr, 1, invlpgb_count_max);
+
+		invlpgb_flush_addr_nosync(addr, nr);
+	}
+	__tlbsync();
 }
 
 static void do_kernel_range_flush(void *info)
@@ -1087,24 +1424,37 @@ static void do_kernel_range_flush(void *info)
 		flush_tlb_one_kernel(addr);
 }
 
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+static void kernel_tlb_flush_all(struct flush_tlb_info *info)
 {
-	/* Balance as user space task's flush, a bit conservative */
-	if (end == TLB_FLUSH_ALL ||
-	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
 		on_each_cpu(do_flush_tlb_all, NULL, 1);
-	} else {
-		struct flush_tlb_info *info;
-
-		preempt_disable();
-		info = get_flush_tlb_info(NULL, start, end, 0, false,
-					  TLB_GENERATION_INVALID);
+}
 
+static void kernel_tlb_flush_range(struct flush_tlb_info *info)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_kernel_range_flush(info);
+	else
 		on_each_cpu(do_kernel_range_flush, info, 1);
+}
 
-		put_flush_tlb_info();
-		preempt_enable();
-	}
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	struct flush_tlb_info *info;
+
+	guard(preempt)();
+
+	info = get_flush_tlb_info(NULL, start, end, PAGE_SHIFT, false,
+				  TLB_GENERATION_INVALID);
+
+	if (info->end == TLB_FLUSH_ALL)
+		kernel_tlb_flush_all(info);
+	else
+		kernel_tlb_flush_range(info);
+
+	put_flush_tlb_info();
 }
 
 /*
@@ -1283,7 +1633,10 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->unmapped_pages) {
+		invlpgb_flush_all_nonglobals();
+		batch->unmapped_pages = false;
+	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
 		flush_tlb_multi(&batch->cpumask, info);
 	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();
@@ -1325,7 +1678,7 @@ bool nmi_uaccess_okay(void)
 	if (loaded_mm != current_mm)
 		return false;
 
-	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+	VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa());
 
 	return true;
 }