Merging upstream version 6.8.12.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

19 files changed, 120 insertions, 123 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6f49999a6b..bfccf12138 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2474,9 +2474,13 @@ menuconfig CPU_MITIGATIONS
 	help
 	  Say Y here to enable options which enable mitigations for hardware
 	  vulnerabilities (usually related to speculative execution).
+	  Mitigations can be disabled or restricted to SMT systems at runtime
+	  via the "mitigations" kernel parameter.
 
-	  If you say N, all mitigations will be disabled. You really
-	  should know what you are doing to say so.
+	  If you say N, all mitigations will be disabled.  This CANNOT be
+	  overridden at runtime.
+
+	  Say 'Y', unless you really know what you are doing.
 
 if CPU_MITIGATIONS
 
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index bf4a10a579..1dcb794c54 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -398,6 +398,11 @@ SYM_CODE_START(startup_64)
 	call	sev_enable
 #endif
 
+	/* Preserve only the CR4 bits that must be preserved, and clear the rest */
+	movq	%cr4, %rax
+	andl	$(X86_CR4_PAE | X86_CR4_MCE | X86_CR4_LA57), %eax
+	movq	%rax, %cr4
+
 	/*
 	 * configure_5level_paging() updates the number of paging levels using
 	 * a trampoline in 32-bit addressable memory if the current number does
diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S
index ef73a3ab87..791386d9a8 100644
--- a/arch/x86/crypto/nh-avx2-x86_64.S
+++ b/arch/x86/crypto/nh-avx2-x86_64.S
@@ -154,5 +154,6 @@ SYM_TYPED_FUNC_START(nh_avx2)
 	vpaddq		T1, T0, T0
 	vpaddq		T4, T0, T0
 	vmovdqu		T0, (HASH)
+	vzeroupper
 	RET
 SYM_FUNC_END(nh_avx2)
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 9918212faf..0ffb072be9 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -716,6 +716,7 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx)
 	popq	%r13
 	popq	%r12
 	popq	%rbx
+	vzeroupper
 	RET
 SYM_FUNC_END(sha256_transform_rorx)
 
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index f08496cd68..24973f42c4 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -680,6 +680,7 @@ SYM_TYPED_FUNC_START(sha512_transform_rorx)
 	pop	%r12
 	pop	%rbx
 
+	vzeroupper
 	RET
 SYM_FUNC_END(sha512_transform_rorx)
 
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index e0ca8120ae..1245000a87 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -98,11 +98,6 @@ static int addr_to_vsyscall_nr(unsigned long addr)
 
 static bool write_ok_or_segv(unsigned long ptr, size_t size)
 {
-	/*
-	 * XXX: if access_ok, get_user, and put_user handled
-	 * sig_on_uaccess_err, this could go away.
-	 */
-
 	if (!access_ok((void __user *)ptr, size)) {
 		struct thread_struct *thread = &current->thread;
 
@@ -120,10 +115,8 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
 bool emulate_vsyscall(unsigned long error_code,
 		      struct pt_regs *regs, unsigned long address)
 {
-	struct task_struct *tsk;
 	unsigned long caller;
 	int vsyscall_nr, syscall_nr, tmp;
-	int prev_sig_on_uaccess_err;
 	long ret;
 	unsigned long orig_dx;
 
@@ -172,8 +165,6 @@ bool emulate_vsyscall(unsigned long error_code,
 		goto sigsegv;
 	}
 
-	tsk = current;
-
 	/*
 	 * Check for access_ok violations and find the syscall nr.
 	 *
@@ -234,12 +225,8 @@ bool emulate_vsyscall(unsigned long error_code,
 		goto do_ret;  /* skip requested */
 
 	/*
-	 * With a real vsyscall, page faults cause SIGSEGV.  We want to
-	 * preserve that behavior to make writing exploits harder.
+	 * With a real vsyscall, page faults cause SIGSEGV.
 	 */
-	prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err;
-	current->thread.sig_on_uaccess_err = 1;
-
 	ret = -EFAULT;
 	switch (vsyscall_nr) {
 	case 0:
@@ -262,23 +249,12 @@ bool emulate_vsyscall(unsigned long error_code,
 		break;
 	}
 
-	current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err;
-
 check_fault:
 	if (ret == -EFAULT) {
 		/* Bad news -- userspace fed a bad pointer to a vsyscall. */
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall fault (exploit attempt?)");
-
-		/*
-		 * If we failed to generate a signal for any reason,
-		 * generate one here.  (This should be impossible.)
-		 */
-		if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
-				 !sigismember(&tsk->pending.signal, SIGSEGV)))
-			goto sigsegv;
-
-		return true;  /* Don't emulate the ret. */
+		goto sigsegv;
 	}
 
 	regs->ax = ret;
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 44b08b53ab..c1d6cd58f8 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -62,7 +62,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old,
 	asm volatile(_lock "cmpxchg16b %[ptr]"				\
 		     CC_SET(e)						\
 		     : CC_OUT(e) (ret),					\
-		       [ptr] "+m" (*ptr),				\
+		       [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
 		     : "memory");					\
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 9abb8cc4cd..b786449626 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -567,6 +567,8 @@ static inline void update_page_count(int level, unsigned long pages) { }
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 				    unsigned int *level);
+pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
+				  unsigned int *level, bool *nx, bool *rw);
 extern pmd_t *lookup_pmd_address(unsigned long address);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 26620d7642..5636ad6973 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -479,7 +479,6 @@ struct thread_struct {
 	unsigned long		iopl_emul;
 
 	unsigned int		iopl_warn:1;
-	unsigned int		sig_on_uaccess_err:1;
 
 	/*
 	 * Protection Keys Register for Userspace.  Loaded immediately on
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 1be13b2dfe..64df897c0e 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -37,8 +37,6 @@ extern int phys_to_target_node(phys_addr_t start);
 #define phys_to_target_node phys_to_target_node
 extern int memory_add_physaddr_to_nid(u64 start);
 #define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
-extern int numa_fill_memblks(u64 start, u64 end);
-#define numa_fill_memblks numa_fill_memblks
 #endif
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 13b45b9c80..620f0af713 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -465,7 +465,7 @@ static bool early_apply_microcode(u32 cpuid_1_eax, u32 old_rev, void *ucode, siz
 	return !__apply_microcode_amd(mc);
 }
 
-static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
+static bool get_builtin_microcode(struct cpio_data *cp, u8 family)
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	struct firmware fw;
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 1123ef3ccf..4334033658 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -193,11 +193,9 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu)
 	cur->warned = false;
 
 	/*
-	 * If a non-zero TSC value for socket 0 may be valid then the default
-	 * adjusted value cannot assumed to be zero either.
+	 * The default adjust value cannot be assumed to be zero on any socket.
 	 */
-	if (tsc_async_resets)
-		cur->adjusted = bootval;
+	cur->adjusted = bootval;
 
 	/*
 	 * Check whether this CPU is the first in a package to come up. In
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 5168ee0360..d1ccd06c53 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -148,7 +148,7 @@ AVXcode:
 65: SEG=GS (Prefix)
 66: Operand-Size (Prefix)
 67: Address-Size (Prefix)
-68: PUSH Iz (d64)
+68: PUSH Iz
 69: IMUL Gv,Ev,Iz
 6a: PUSH Ib (d64)
 6b: IMUL Gv,Ev,Ib
@@ -698,10 +698,10 @@ AVXcode: 2
 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-50: vpdpbusd Vx,Hx,Wx (66),(ev)
-51: vpdpbusds Vx,Hx,Wx (66),(ev)
-52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
-53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
+50: vpdpbusd Vx,Hx,Wx (66)
+51: vpdpbusds Vx,Hx,Wx (66)
+52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
+53: vpdpwssds Vx,Hx,Wx (66) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
 54: vpopcntb/w Vx,Wx (66),(ev)
 55: vpopcntd/q Vx,Wx (66),(ev)
 58: vpbroadcastd Vx,Wx (66),(v)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b01df023de..e604d2d6cc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -717,39 +717,8 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code,
 	WARN_ON_ONCE(user_mode(regs));
 
 	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
-		/*
-		 * Any interrupt that takes a fault gets the fixup. This makes
-		 * the below recursive fault logic only apply to a faults from
-		 * task context.
-		 */
-		if (in_interrupt())
-			return;
-
-		/*
-		 * Per the above we're !in_interrupt(), aka. task context.
-		 *
-		 * In this case we need to make sure we're not recursively
-		 * faulting through the emulate_vsyscall() logic.
-		 */
-		if (current->thread.sig_on_uaccess_err && signal) {
-			sanitize_error_code(address, &error_code);
-
-			set_signal_archinfo(address, error_code);
-
-			if (si_code == SEGV_PKUERR) {
-				force_sig_pkuerr((void __user *)address, pkey);
-			} else {
-				/* XXX: hwpoison faults will set the wrong code. */
-				force_sig_fault(signal, si_code, (void __user *)address);
-			}
-		}
-
-		/*
-		 * Barring that, we can do the fixup and be happy.
-		 */
+	if (fixup_exception(regs, X86_TRAP_PF, error_code, address))
 		return;
-	}
 
 	/*
 	 * AMD erratum #91 manifests as a spurious page fault on a PREFETCH
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 65e9a6e391..ce84ba86e6 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -929,6 +929,8 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 
+#endif
+
 static int __init cmp_memblk(const void *a, const void *b)
 {
 	const struct numa_memblk *ma = *(const struct numa_memblk **)a;
@@ -1001,5 +1003,3 @@ int __init numa_fill_memblks(u64 start, u64 end)
 	}
 	return 0;
 }
-
-#endif
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 135bb594df..b4073fb452 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -619,7 +619,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start,
  * Validate strict W^X semantics.
  */
 static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start,
-				  unsigned long pfn, unsigned long npg)
+				  unsigned long pfn, unsigned long npg,
+				  bool nx, bool rw)
 {
 	unsigned long end;
 
@@ -641,6 +642,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
 	if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW)
 		return new;
 
+	/* Non-leaf translation entries can disable writing or execution. */
+	if (!rw || nx)
+		return new;
+
 	end = start + npg * PAGE_SIZE - 1;
 	WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n",
 		  (unsigned long long)pgprot_val(old),
@@ -657,20 +662,26 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
 
 /*
  * Lookup the page table entry for a virtual address in a specific pgd.
- * Return a pointer to the entry and the level of the mapping.
+ * Return a pointer to the entry, the level of the mapping, and the effective
+ * NX and RW bits of all page table levels.
  */
-pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
-			     unsigned int *level)
+pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
+				  unsigned int *level, bool *nx, bool *rw)
 {
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
 	*level = PG_LEVEL_NONE;
+	*nx = false;
+	*rw = true;
 
 	if (pgd_none(*pgd))
 		return NULL;
 
+	*nx |= pgd_flags(*pgd) & _PAGE_NX;
+	*rw &= pgd_flags(*pgd) & _PAGE_RW;
+
 	p4d = p4d_offset(pgd, address);
 	if (p4d_none(*p4d))
 		return NULL;
@@ -679,6 +690,9 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 	if (p4d_large(*p4d) || !p4d_present(*p4d))
 		return (pte_t *)p4d;
 
+	*nx |= p4d_flags(*p4d) & _PAGE_NX;
+	*rw &= p4d_flags(*p4d) & _PAGE_RW;
+
 	pud = pud_offset(p4d, address);
 	if (pud_none(*pud))
 		return NULL;
@@ -687,6 +701,9 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 	if (pud_leaf(*pud) || !pud_present(*pud))
 		return (pte_t *)pud;
 
+	*nx |= pud_flags(*pud) & _PAGE_NX;
+	*rw &= pud_flags(*pud) & _PAGE_RW;
+
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd))
 		return NULL;
@@ -695,12 +712,27 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 	if (pmd_large(*pmd) || !pmd_present(*pmd))
 		return (pte_t *)pmd;
 
+	*nx |= pmd_flags(*pmd) & _PAGE_NX;
+	*rw &= pmd_flags(*pmd) & _PAGE_RW;
+
 	*level = PG_LEVEL_4K;
 
 	return pte_offset_kernel(pmd, address);
 }
 
 /*
+ * Lookup the page table entry for a virtual address in a specific pgd.
+ * Return a pointer to the entry and the level of the mapping.
+ */
+pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+			     unsigned int *level)
+{
+	bool nx, rw;
+
+	return lookup_address_in_pgd_attr(pgd, address, level, &nx, &rw);
+}
+
+/*
  * Lookup the page table entry for a virtual address. Return a pointer
  * to the entry and the level of the mapping.
  *
@@ -715,13 +747,16 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 EXPORT_SYMBOL_GPL(lookup_address);
 
 static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
-				  unsigned int *level)
+				  unsigned int *level, bool *nx, bool *rw)
 {
-	if (cpa->pgd)
-		return lookup_address_in_pgd(cpa->pgd + pgd_index(address),
-					       address, level);
+	pgd_t *pgd;
+
+	if (!cpa->pgd)
+		pgd = pgd_offset_k(address);
+	else
+		pgd = cpa->pgd + pgd_index(address);
 
-	return lookup_address(address, level);
+	return lookup_address_in_pgd_attr(pgd, address, level, nx, rw);
 }
 
 /*
@@ -849,12 +884,13 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
 	pgprot_t old_prot, new_prot, req_prot, chk_prot;
 	pte_t new_pte, *tmp;
 	enum pg_level level;
+	bool nx, rw;
 
 	/*
 	 * Check for races, another CPU might have split this page
 	 * up already:
 	 */
-	tmp = _lookup_address_cpa(cpa, address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
 	if (tmp != kpte)
 		return 1;
 
@@ -965,7 +1001,8 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
 	new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
 				      psize, CPA_DETECT);
 
-	new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages);
+	new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages,
+			      nx, rw);
 
 	/*
 	 * If there is a conflict, split the large page.
@@ -1046,6 +1083,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 	pte_t *pbase = (pte_t *)page_address(base);
 	unsigned int i, level;
 	pgprot_t ref_prot;
+	bool nx, rw;
 	pte_t *tmp;
 
 	spin_lock(&pgd_lock);
@@ -1053,7 +1091,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 	 * Check for races, another CPU might have split this page
 	 * up for us already:
 	 */
-	tmp = _lookup_address_cpa(cpa, address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
 	if (tmp != kpte) {
 		spin_unlock(&pgd_lock);
 		return 1;
@@ -1594,10 +1632,11 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 	int do_split, err;
 	unsigned int level;
 	pte_t *kpte, old_pte;
+	bool nx, rw;
 
 	address = __cpa_addr(cpa, cpa->curpage);
 repeat:
-	kpte = _lookup_address_cpa(cpa, address, &level);
+	kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
 	if (!kpte)
 		return __cpa_process_fault(cpa, address, primary);
 
@@ -1619,7 +1658,8 @@ repeat:
 		new_prot = static_protections(new_prot, address, pfn, 1, 0,
 					      CPA_PROTECT);
 
-		new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1);
+		new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1,
+				      nx, rw);
 
 		new_prot = pgprot_clear_protnone_bits(new_prot);
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index df484885cc..f415c2cf53 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1585,36 +1585,41 @@ st:			if (is_imm8(insn->off))
 			if (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
 			    BPF_MODE(insn->code) == BPF_PROBE_MEMSX) {
 				/* Conservatively check that src_reg + insn->off is a kernel address:
-				 *   src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE
-				 * src_reg is used as scratch for src_reg += insn->off and restored
-				 * after emit_ldx if necessary
+				 *   src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE
+				 *   and
+				 *   src_reg + insn->off < VSYSCALL_ADDR
 				 */
 
-				u64 limit = TASK_SIZE_MAX + PAGE_SIZE;
+				u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR;
 				u8 *end_of_jmp;
 
-				/* At end of these emitted checks, insn->off will have been added
-				 * to src_reg, so no need to do relative load with insn->off offset
-				 */
-				insn_off = 0;
+				/* movabsq r10, VSYSCALL_ADDR */
+				emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32,
+					       (u32)(long)VSYSCALL_ADDR);
 
-				/* movabsq r11, limit */
-				EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG));
-				EMIT((u32)limit, 4);
-				EMIT(limit >> 32, 4);
+				/* mov src_reg, r11 */
+				EMIT_mov(AUX_REG, src_reg);
 
 				if (insn->off) {
-					/* add src_reg, insn->off */
-					maybe_emit_1mod(&prog, src_reg, true);
-					EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off);
+					/* add r11, insn->off */
+					maybe_emit_1mod(&prog, AUX_REG, true);
+					EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off);
 				}
 
-				/* cmp src_reg, r11 */
-				maybe_emit_mod(&prog, src_reg, AUX_REG, true);
-				EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG));
+				/* sub r11, r10 */
+				maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true);
+				EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX));
+
+				/* movabsq r10, limit */
+				emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32,
+					       (u32)(long)limit);
+
+				/* cmp r10, r11 */
+				maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true);
+				EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX));
 
-				/* if unsigned '>=', goto load */
-				EMIT2(X86_JAE, 0);
+				/* if unsigned '>', goto load */
+				EMIT2(X86_JA, 0);
 				end_of_jmp = prog;
 
 				/* xor dst_reg, dst_reg */
@@ -1640,18 +1645,6 @@ st:			if (is_imm8(insn->off))
 				/* populate jmp_offset for JMP above */
 				start_of_ldx[-1] = prog - start_of_ldx;
 
-				if (insn->off && src_reg != dst_reg) {
-					/* sub src_reg, insn->off
-					 * Restore src_reg after "add src_reg, insn->off" in prev
-					 * if statement. But if src_reg == dst_reg, emit_ldx
-					 * above already clobbered src_reg, so no need to restore.
-					 * If add src_reg, insn->off was unnecessary, no need to
-					 * restore either.
-					 */
-					maybe_emit_1mod(&prog, src_reg, true);
-					EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off);
-				}
-
 				if (!bpf_prog->aux->extable)
 					break;
 
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 08aa0f25f1..8d1c82795e 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -42,7 +42,8 @@ KCOV_INSTRUMENT := n
 # make up the standalone purgatory.ro
 
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
-PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -g0
+PURGATORY_CFLAGS := -mcmodel=small -ffreestanding -fno-zero-initialized-in-bss -g0
+PURGATORY_CFLAGS += -fpic -fvisibility=hidden
 PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
 PURGATORY_CFLAGS += -fno-stack-protector
 
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index b029fb81eb..e7a44a7f61 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -746,6 +746,15 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) {
 			continue;
 		}
+
+		/*
+		 * Do not perform relocations in .notes sections; any
+		 * values there are meant for pre-boot consumption (e.g.
+		 * startup_xen).
+		 */
+		if (sec_applies->shdr.sh_type == SHT_NOTE)
+			continue;
+
 		sh_symtab = sec_symtab->symtab;
 		sym_strtab = sec_symtab->link->strtab;
 		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {