x86/jump_label: Initialize static branching early

Static branching is useful to runtime patch branches that are used in hot
path, but are infrequently changed.

The x86 clock framework is one example that uses static branches to setup
the best clock during boot and never changes it again.

It is desired to enable the TSC based sched clock early to allow fine
grained boot time analysis early on. That requires the static branching
functionality to be functional early as well.

Static branching requires patching nop instructions, thus,
arch_init_ideal_nops() must be called prior to jump_label_init().

Do all the necessary steps to call arch_init_ideal_nops() right after
early_cpu_init(), which also allows to insert a call to jump_label_init()
right after that. jump_label_init() will be called again from the generic
init code, but the code is protected against reinitialization already.

[ tglx: Massaged changelog ]

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-10-pasha.tatashin@oracle.com

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 38915fbfae73d5cfeacbf16624fa49cb9edc7ec7..b732438c1a1ef567614277519597321eb7dd637b 100644 (file)
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -232,8 +232,6 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
                }
        }
 
-       set_cpu_cap(c, X86_FEATURE_K7);
-
        /* calling is from identify_secondary_cpu() ? */
        if (!c->cpu_index)
                return;
@@ -617,6 +615,14 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 
        early_init_amd_mc(c);
 
+#ifdef CONFIG_X86_32
+       if (c->x86 == 6)
+               set_cpu_cap(c, X86_FEATURE_K7);
+#endif
+
+       if (c->x86 >= 0xf)
+               set_cpu_cap(c, X86_FEATURE_K8);
+
        rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
 
        /*
@@ -863,9 +869,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 
        init_amd_cacheinfo(c);
 
-       if (c->x86 >= 0xf)
-               set_cpu_cap(c, X86_FEATURE_K8);
-
        if (cpu_has(c, X86_FEATURE_XMM2)) {
                unsigned long long val;
                int ret;

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index eb4cb3efd20e4cd5ec31d90c1dcf88b62b94622b..71281ac43b15f8e86ab365cd54d4f23e45e67d74 100644 (file)
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1015,6 +1015,24 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
        setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 }
 
+/*
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
+ * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
+ */
+static void detect_nopl(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_32
+       clear_cpu_cap(c, X86_FEATURE_NOPL);
+#else
+       set_cpu_cap(c, X86_FEATURE_NOPL);
+#endif
+}
+
 /*
  * Do minimum CPU detection early.
  * Fields really needed: vendor, cpuid_level, family, model, mask,
@@ -1089,6 +1107,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
         */
        if (!pgtable_l5_enabled())
                setup_clear_cpu_cap(X86_FEATURE_LA57);
+
+       detect_nopl(c);
 }
 
 void __init early_cpu_init(void)
@@ -1124,24 +1144,6 @@ void __init early_cpu_init(void)
        early_identify_cpu(&boot_cpu_data);
 }
 
-/*
- * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
- * unfortunately, that's not true in practice because of early VIA
- * chips and (more importantly) broken virtualizers that are not easy
- * to detect. In the latter case it doesn't even *fail* reliably, so
- * probing for it doesn't even work. Disable it completely on 32-bit
- * unless we can find a reliable way to detect all the broken cases.
- * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
- */
-static void detect_nopl(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_X86_32
-       clear_cpu_cap(c, X86_FEATURE_NOPL);
-#else
-       set_cpu_cap(c, X86_FEATURE_NOPL);
-#endif
-}
-
 static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_64

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index da1dbd99cb6eec923c4532209606ef2159bcd1f0..7490de925a811f34f977faf5b0aff6007700230f 100644 (file)
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -866,6 +866,8 @@ void __init setup_arch(char **cmdline_p)
 
        idt_setup_early_traps();
        early_cpu_init();
+       arch_init_ideal_nops();
+       jump_label_init();
        early_ioremap_init();
 
        setup_olpc_ofw_pgd();
@@ -1268,8 +1270,6 @@ void __init setup_arch(char **cmdline_p)
 
        mcheck_init();
 
-       arch_init_ideal_nops();
-
        register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI