From: Andy Lutomirski Date: Mon, 11 Sep 2017 00:48:27 +0000 (-0700) Subject: x86/mm/64: Initialize CR4.PCIDE early X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=c7ad5ad297e644601747d6dbee978bf85e14f7bc;p=GitHub%2Fmoto-9609%2Fandroid_kernel_motorola_exynos9610.git x86/mm/64: Initialize CR4.PCIDE early cpu_init() is weird: it's called rather late (after early identification and after most MMU state is initialized) on the boot CPU but is called extremely early (before identification) on secondary CPUs. It's called just late enough on the boot CPU that its CR4 value isn't propagated to mmu_cr4_features. Even if we put CR4.PCIDE into mmu_cr4_features, we'd hit two problems. First, we'd crash in the trampoline code. That's fixable, and I tried that. It turns out that mmu_cr4_features is totally ignored by secondary_start_64(), though, so even with the trampoline code fixed, it wouldn't help. This means that we don't currently have CR4.PCIDE reliably initialized before we start playing with cpu_tlbstate. This is very fragile and tends to cause boot failures if I make even small changes to the TLB handling code. Make it more robust: initialize CR4.PCIDE earlier on the boot CPU and propagate it to secondary CPUs in start_secondary(). ( Yes, this is ugly. I think we should have improved mmu_cr4_features to actually control CR4 during secondary bootup, but that would be fairly intrusive at this stage. ) Signed-off-by: Andy Lutomirski Reported-by: Sai Praneeth Prakhya Tested-by: Sai Praneeth Prakhya Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Fixes: 660da7c9228f ("x86/mm: Enable CR4.PCIDE on supported systems") Signed-off-by: Ingo Molnar --- diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index fb1d3358a4af..775f10100d7f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -169,21 +169,21 @@ static int __init x86_mpx_setup(char *s) __setup("nompx", x86_mpx_setup); #ifdef CONFIG_X86_64 -static int __init x86_pcid_setup(char *s) +static int __init x86_nopcid_setup(char *s) { - /* require an exact match without trailing characters */ - if (strlen(s)) - return 0; + /* nopcid doesn't accept parameters */ + if (s) + return -EINVAL; /* do not emit a message if the feature is not present */ if (!boot_cpu_has(X86_FEATURE_PCID)) - return 1; + return 0; setup_clear_cpu_cap(X86_FEATURE_PCID); pr_info("nopcid: PCID feature disabled\n"); - return 1; + return 0; } -__setup("nopcid", x86_pcid_setup); +early_param("nopcid", x86_nopcid_setup); #endif static int __init x86_noinvpcid_setup(char *s) @@ -329,38 +329,6 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) } } -static void setup_pcid(struct cpuinfo_x86 *c) -{ - if (cpu_has(c, X86_FEATURE_PCID)) { - if (cpu_has(c, X86_FEATURE_PGE)) { - /* - * We'd like to use cr4_set_bits_and_update_boot(), - * but we can't. CR4.PCIDE is special and can only - * be set in long mode, and the early CPU init code - * doesn't know this and would try to restore CR4.PCIDE - * prior to entering long mode. - * - * Instead, we rely on the fact that hotplug, resume, - * etc all fully restore CR4 before they write anything - * that could have nonzero PCID bits to CR3. CR4.PCIDE - * has no effect on the page tables themselves, so we - * don't need it to be restored early. - */ - cr4_set_bits(X86_CR4_PCIDE); - } else { - /* - * flush_tlb_all(), as currently implemented, won't - * work if PCID is on but PGE is not. Since that - * combination doesn't exist on real hardware, there's - * no reason to try to fully support it, but it's - * polite to avoid corrupting data if we're on - * an improperly configured VM. - */ - clear_cpu_cap(c, X86_FEATURE_PCID); - } - } -} - /* * Protection Keys are not available in 32-bit mode. */ @@ -1175,9 +1143,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) setup_smep(c); setup_smap(c); - /* Set up PCID */ - setup_pcid(c); - /* * The vendor-specific functions might have changed features. * Now we do "generic changes." diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d84afb0a322d..0957dd73d127 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1178,8 +1178,11 @@ void __init setup_arch(char **cmdline_p) * with the current CR4 value. This may not be necessary, but * auditing all the early-boot CR4 manipulation would be needed to * rule it out. + * + * Mask off features that don't work outside long mode (just + * PCIDE for now). */ - mmu_cr4_features = __read_cr4(); + mmu_cr4_features = __read_cr4() & ~X86_CR4_PCIDE; memblock_set_current_limit(get_max_mapped()); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index cd6622c3204e..0854ff169274 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -226,10 +226,12 @@ static int enable_start_cpu0; static void notrace start_secondary(void *unused) { /* - * Don't put *anything* before cpu_init(), SMP booting is too - * fragile that we want to limit the things done here to the - * most necessary things. + * Don't put *anything* except direct CPU state initialization + * before cpu_init(), SMP booting is too fragile that we want to + * limit the things done here to the most necessary things. */ + if (boot_cpu_has(X86_FEATURE_PCID)) + __write_cr4(__read_cr4() | X86_CR4_PCIDE); cpu_init(); x86_cpuinit.early_percpu_clock_init(); preempt_disable(); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 7777ccc0e9f9..af5c1ed21d43 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -19,6 +19,7 @@ #include #include #include +#include /* * We need to define the tracepoints somewhere, and tlb.c @@ -193,6 +194,38 @@ static void __init probe_page_size_mask(void) } } +static void setup_pcid(void) +{ +#ifdef CONFIG_X86_64 + if (boot_cpu_has(X86_FEATURE_PCID)) { + if (boot_cpu_has(X86_FEATURE_PGE)) { + /* + * This can't be cr4_set_bits_and_update_boot() -- + * the trampoline code can't handle CR4.PCIDE and + * it wouldn't do any good anyway. Despite the name, + * cr4_set_bits_and_update_boot() doesn't actually + * cause the bits in question to remain set all the + * way through the secondary boot asm. + * + * Instead, we brute-force it and set CR4.PCIDE + * manually in start_secondary(). + */ + cr4_set_bits(X86_CR4_PCIDE); + } else { + /* + * flush_tlb_all(), as currently implemented, won't + * work if PCID is on but PGE is not. Since that + * combination doesn't exist on real hardware, there's + * no reason to try to fully support it, but it's + * polite to avoid corrupting data if we're on + * an improperly configured VM. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); + } + } +#endif +} + #ifdef CONFIG_X86_32 #define NR_RANGE_MR 3 #else /* CONFIG_X86_64 */ @@ -592,6 +625,7 @@ void __init init_mem_mapping(void) unsigned long end; probe_page_size_mask(); + setup_pcid(); #ifdef CONFIG_X86_64 end = max_pfn << PAGE_SHIFT;