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

Pull x86 fixes from Ingo Molnar:

 - Fix a performance regression on AMD iGPU and dGPU drivers, related to
   the unintended activation of DMA bounce buffers that regressed game
   performance if KASLR disturbed things just enough

 - Fix a copy_user_generic() performance regression on certain older
   non-FSRM/ERMS CPUs

 - Fix a Clang build warning due to a semantic merge conflict the Kunit
   tree generated with the x86 tree

 - Fix FRED related system hang during S4 resume

 - Remove an unused API

* tag 'x86-urgent-2025-04-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fred: Fix system hang during S4 resume with FRED enabled
  x86/platform/iosf_mbi: Remove unused iosf_mbi_unregister_pmic_bus_access_notifier()
  x86/mm/init: Handle the special case of device private pages in add_pages(), to not increase max_pfn and trigger dma_addressing_limited() bounce buffers
  x86/tools: Drop duplicate unlikely() definition in insn_decoder_test.c
  x86/uaccess: Improve performance by aligning writes to 8 bytes in copy_user_generic(), on non-FSRM/ERMS CPUs

Author: torvalds

arch/x86/include/asm/iosf_mbi.h

@@ -167,13 +167,6 @@ void iosf_mbi_unblock_punit_i2c_access(void);
  */
 int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb);
 
-/**
- * iosf_mbi_register_pmic_bus_access_notifier - Unregister PMIC bus notifier
- *
- * @nb: notifier_block to unregister
- */
-int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb);
-
 /**
  * iosf_mbi_unregister_pmic_bus_access_notifier_unlocked - Unregister PMIC bus
  *                                                         notifier, unlocked

arch/x86/lib/copy_user_64.S

@@ -77,6 +77,24 @@ SYM_FUNC_START(rep_movs_alternative)
 	_ASM_EXTABLE_UA( 0b, 1b)
 
 .Llarge_movsq:
+	/* Do the first possibly unaligned word */
+0:	movq (%rsi),%rax
+1:	movq %rax,(%rdi)
+
+	_ASM_EXTABLE_UA( 0b, .Lcopy_user_tail)
+	_ASM_EXTABLE_UA( 1b, .Lcopy_user_tail)
+
+	/* What would be the offset to the aligned destination? */
+	leaq 8(%rdi),%rax
+	andq $-8,%rax
+	subq %rdi,%rax
+
+	/* .. and update pointers and count to match */
+	addq %rax,%rdi
+	addq %rax,%rsi
+	subq %rax,%rcx
+
+	/* make %rcx contain the number of words, %rax the remainder */
 	movq %rcx,%rax
 	shrq $3,%rcx
 	andl $7,%eax

arch/x86/mm/init_64.c

@@ -959,9 +959,18 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	ret = __add_pages(nid, start_pfn, nr_pages, params);
 	WARN_ON_ONCE(ret);
 
-	/* update max_pfn, max_low_pfn and high_memory */
-	update_end_of_memory_vars(start_pfn << PAGE_SHIFT,
-				  nr_pages << PAGE_SHIFT);
+	/*
+	 * Special case: add_pages() is called by memremap_pages() for adding device
+	 * private pages. Do not bump up max_pfn in the device private path,
+	 * because max_pfn changes affect dma_addressing_limited().
+	 *
+	 * dma_addressing_limited() returning true when max_pfn is the device's
+	 * addressable memory can force device drivers to use bounce buffers
+	 * and impact their performance negatively:
+	 */
+	if (!params->pgmap)
+		/* update max_pfn, max_low_pfn and high_memory */
+		update_end_of_memory_vars(start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
 
 	return ret;
 }

arch/x86/platform/intel/iosf_mbi.c

@@ -422,19 +422,6 @@ int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(
 }
 EXPORT_SYMBOL(iosf_mbi_unregister_pmic_bus_access_notifier_unlocked);
 
-int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb)
-{
-	int ret;
-
-	/* Wait for the bus to go inactive before unregistering */
-	iosf_mbi_punit_acquire();
-	ret = iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(nb);
-	iosf_mbi_punit_release();
-
-	return ret;
-}
-EXPORT_SYMBOL(iosf_mbi_unregister_pmic_bus_access_notifier);
-
 void iosf_mbi_assert_punit_acquired(void)
 {
 	WARN_ON(iosf_mbi_pmic_punit_access_count == 0);

arch/x86/power/cpu.c

@@ -27,6 +27,7 @@
 #include <asm/mmu_context.h>
 #include <asm/cpu_device_id.h>
 #include <asm/microcode.h>
+#include <asm/fred.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -231,6 +232,19 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	 */
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+
+	/*
+	 * Reinitialize FRED to ensure the FRED MSRs contain the same values
+	 * as before hibernation.
+	 *
+	 * Note, the setup of FRED RSPs requires access to percpu data
+	 * structures.  Therefore, FRED reinitialization can only occur after
+	 * the percpu access pointer (i.e., MSR_GS_BASE) is restored.
+	 */
+	if (ctxt->cr4 & X86_CR4_FRED) {
+		cpu_init_fred_exceptions();
+		cpu_init_fred_rsps();
+	}
 #else
 	loadsegment(fs, __KERNEL_PERCPU);
 #endif

arch/x86/tools/insn_decoder_test.c

@@ -12,8 +12,6 @@
 #include <stdarg.h>
 #include <linux/kallsyms.h>
 
-#define unlikely(cond) (cond)
-
 #include <asm/insn.h>
 #include <inat.c>
 #include <insn.c>

drivers/gpu/drm/i915/i915_iosf_mbi.h

@@ -31,12 +31,6 @@ iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(struct notifier_block *nb)
 {
 	return 0;
 }
-
-static inline
-int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
 #endif
 
 #endif /* __I915_IOSF_MBI_H__ */