Merge tag 'x86_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - AMD Memory bandwidth counter width fix, by Babu Moger.

 - Use the proper length type in the 32-bit truncate() syscall variant,
   by Jiri Slaby.

 - Reinit IA32_FEAT_CTL during wakeup to fix the case where after
   resume, VMXON would #GP due to VMX not being properly enabled, by
   Sean Christopherson.

 - Fix a static checker warning in the resctrl code, by Dan Carpenter.

 - Add a CR4 pinning mask for bits which cannot change after boot, by
   Kees Cook.

 - Align the start of the loop of __clear_user() to 16 bytes, to improve
   performance on AMD zen1 and zen2 microarchitectures, by Matt Fleming.

* tag 'x86_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/asm/64: Align start of __clear_user() loop to 16-bytes
  x86/cpu: Use pinning mask for CR4 bits needing to be 0
  x86/resctrl: Fix a NULL vs IS_ERR() static checker warning in rdt_cdp_peer_get()
  x86/cpu: Reinitialize IA32_FEAT_CTL MSR on BSP during wakeup
  syscalls: Fix offset type of ksys_ftruncate()
  x86/resctrl: Fix memory bandwidth counter width for AMD

arch/x86/include/asm/cpu.h

@@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip)
 	return false;
 }
 #endif
+#ifdef CONFIG_IA32_FEAT_CTL
+void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
+#else
+static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
+#endif
 #endif /* _ASM_X86_CPU_H */

arch/x86/kernel/cpu/centaur.c

@@ -3,6 +3,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/e820/api.h>
 #include <asm/mtrr.h>

arch/x86/kernel/cpu/common.c

@@ -347,6 +347,9 @@ static __always_inline void setup_umip(struct cpuinfo_x86 *c)
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
+/* These bits should not change their value after CPU init is finished. */
+static const unsigned long cr4_pinned_mask =
+	X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE;
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
@@ -371,20 +374,20 @@ EXPORT_SYMBOL(native_write_cr0);
 
 void native_write_cr4(unsigned long val)
 {
-	unsigned long bits_missing = 0;
+	unsigned long bits_changed = 0;
 
 set_register:
 	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
 
 	if (static_branch_likely(&cr_pinning)) {
-		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
-			bits_missing = ~val & cr4_pinned_bits;
-			val |= bits_missing;
+		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {
+			bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits;
+			val = (val & ~cr4_pinned_mask) | cr4_pinned_bits;
 			goto set_register;
 		}
-		/* Warn after we've set the missing bits. */
-		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
-			  bits_missing);
+		/* Warn after we've corrected the changed bits. */
+		WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n",
+			  bits_changed);
 	}
 }
 #if IS_MODULE(CONFIG_LKDTM)
@@ -419,7 +422,7 @@ void cr4_init(void)
 	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4 |= X86_CR4_PCIDE;
 	if (static_branch_likely(&cr_pinning))
-		cr4 |= cr4_pinned_bits;
+		cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits;
 
 	__write_cr4(cr4);
 
@@ -434,10 +437,7 @@ void cr4_init(void)
  */
 static void __init setup_cr_pinning(void)
 {
-	unsigned long mask;
-
-	mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP);
-	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask;
+	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask;
 	static_key_enable(&cr_pinning.key);
 }
 

arch/x86/kernel/cpu/cpu.h

@@ -81,8 +81,4 @@ extern void update_srbds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
-#ifdef CONFIG_IA32_FEAT_CTL
-void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
-#endif
-
 #endif /* ARCH_X86_CPU_H */

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

@@ -981,10 +981,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 
 		c->x86_cache_max_rmid  = ecx;
 		c->x86_cache_occ_scale = ebx;
-		if (c->x86_vendor == X86_VENDOR_INTEL)
 		c->x86_cache_mbm_width_offset = eax & 0xff;
-		else
-			c->x86_cache_mbm_width_offset = -1;
+
+		if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset)
+			c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD;
 	}
 }
 

arch/x86/kernel/cpu/resctrl/internal.h

@@ -37,6 +37,7 @@
 #define MBA_IS_LINEAR			0x4
 #define MBA_MAX_MBPS			U32_MAX
 #define MAX_MBA_BW_AMD			0x800
+#define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)

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

@@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
 	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
 	if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
 		_r_cdp = NULL;
+		_d_cdp = NULL;
 		ret = -EINVAL;
 	}
 

arch/x86/kernel/cpu/zhaoxin.c

@@ -2,6 +2,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 
 #include "cpu.h"

arch/x86/lib/usercopy_64.c

@@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 	asm volatile(
 		"	testq  %[size8],%[size8]\n"
 		"	jz     4f\n"
+		"	.align 16\n"
 		"0:	movq $0,(%[dst])\n"
 		"	addq   $8,%[dst]\n"
 		"	decl %%ecx ; jnz   0b\n"

arch/x86/power/cpu.c

@@ -193,6 +193,8 @@ static void fix_processor_context(void)
  */
 static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
+	struct cpuinfo_x86 *c;
+
 	if (ctxt->misc_enable_saved)
 		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
 	/*
@@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	mtrr_bp_restore();
 	perf_restore_debug_store();
 	msr_restore_context(ctxt);
+
+	c = &cpu_data(smp_processor_id());
+	if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL))
+		init_ia32_feat_ctl(c);
 }
 
 /* Needed by apm.c */

include/linux/syscalls.h

@@ -1360,7 +1360,7 @@ static inline long ksys_lchown(const char __user *filename, uid_t user,
 
 extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 
-static inline long ksys_ftruncate(unsigned int fd, unsigned long length)
+static inline long ksys_ftruncate(unsigned int fd, loff_t length)
 {
 	return do_sys_ftruncate(fd, length, 1);
 }