Merge tag 'x86_urgent_for_v5.13-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:
 "A bunch of x86/urgent stuff accumulated for the last two weeks so
  lemme unload it to you.

  It should be all totally risk-free, of course. :-)

   - Fix out-of-spec hardware (1st gen Hygon) which does not implement
     MSR_AMD64_SEV even though the spec clearly states so, and check
     CPUID bits first.

   - Send only one signal to a task when it is a SEGV_PKUERR si_code
     type.

   - Do away with all the wankery of reserving X amount of memory in the
     first megabyte to prevent BIOS corrupting it and simply and
     unconditionally reserve the whole first megabyte.

   - Make alternatives NOP optimization work at an arbitrary position
     within the patched sequence because the compiler can put
     single-byte NOPs for alignment anywhere in the sequence (32-bit
     retpoline), vs our previous assumption that the NOPs are only
     appended.

   - Force-disable ENQCMD[S] instructions support and remove
     update_pasid() because of insufficient protection against FPU state
     modification in an interrupt context, among other xstate horrors
     which are being addressed at the moment. This one limits the
     fallout until proper enablement.

   - Use cpu_feature_enabled() in the idxd driver so that it can be
     build-time disabled through the defines in disabled-features.h.

   - Fix LVT thermal setup for SMI delivery mode by making sure the APIC
     LVT value is read before APIC initialization so that softlockups
     during boot do not happen at least on one machine.

   - Mark all legacy interrupts as legacy vectors when the IO-APIC is
     disabled and when all legacy interrupts are routed through the PIC"

* tag 'x86_urgent_for_v5.13-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/sev: Check SME/SEV support in CPUID first
  x86/fault: Don't send SIGSEGV twice on SEGV_PKUERR
  x86/setup: Always reserve the first 1M of RAM
  x86/alternative: Optimize single-byte NOPs at an arbitrary position
  x86/cpufeatures: Force disable X86_FEATURE_ENQCMD and remove update_pasid()
  dmaengine: idxd: Use cpu_feature_enabled()
  x86/thermal: Fix LVT thermal setup for SMI delivery mode
  x86/apic: Mark _all_ legacy interrupts when IO/APIC is missing

1 files changed, 30 insertions, 14 deletions

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 72920af0b3c0..1e720626069a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -44,6 +44,7 @@
 #include <asm/pci-direct.h>
 #include <asm/prom.h>
 #include <asm/proto.h>
+#include <asm/thermal.h>
 #include <asm/unwind.h>
 #include <asm/vsyscall.h>
 #include <linux/vmalloc.h>
@@ -637,11 +638,11 @@ static void __init trim_snb_memory(void)
 	 * them from accessing certain memory ranges, namely anything below
 	 * 1M and in the pages listed in bad_pages[] above.
 	 *
-	 * To avoid these pages being ever accessed by SNB gfx devices
-	 * reserve all memory below the 1 MB mark and bad_pages that have
-	 * not already been reserved at boot time.
+	 * To avoid these pages being ever accessed by SNB gfx devices reserve
+	 * bad_pages that have not already been reserved at boot time.
+	 * All memory below the 1 MB mark is anyway reserved later during
+	 * setup_arch(), so there is no need to reserve it here.
 	 */
-	memblock_reserve(0, 1<<20);
 
 	for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
 		if (memblock_reserve(bad_pages[i], PAGE_SIZE))
@@ -733,14 +734,14 @@ static void __init early_reserve_memory(void)
 	 * The first 4Kb of memory is a BIOS owned area, but generally it is
 	 * not listed as such in the E820 table.
 	 *
-	 * Reserve the first memory page and typically some additional
-	 * memory (64KiB by default) since some BIOSes are known to corrupt
-	 * low memory. See the Kconfig help text for X86_RESERVE_LOW.
+	 * Reserve the first 64K of memory since some BIOSes are known to
+	 * corrupt low memory. After the real mode trampoline is allocated the
+	 * rest of the memory below 640k is reserved.
 	 *
 	 * In addition, make sure page 0 is always reserved because on
 	 * systems with L1TF its contents can be leaked to user processes.
 	 */
-	memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE));
+	memblock_reserve(0, SZ_64K);
 
 	early_reserve_initrd();
 
@@ -751,6 +752,7 @@ static void __init early_reserve_memory(void)
 
 	reserve_ibft_region();
 	reserve_bios_regions();
+	trim_snb_memory();
 }
 
 /*
@@ -1081,14 +1083,20 @@ void __init setup_arch(char **cmdline_p)
 			(max_pfn_mapped<<PAGE_SHIFT) - 1);
 #endif
 
-	reserve_real_mode();
-
 	/*
-	 * Reserving memory causing GPU hangs on Sandy Bridge integrated
-	 * graphics devices should be done after we allocated memory under
-	 * 1M for the real mode trampoline.
+	 * Find free memory for the real mode trampoline and place it
+	 * there.
+	 * If there is not enough free memory under 1M, on EFI-enabled
+	 * systems there will be additional attempt to reclaim the memory
+	 * for the real mode trampoline at efi_free_boot_services().
+	 *
+	 * Unconditionally reserve the entire first 1M of RAM because
+	 * BIOSes are know to corrupt low memory and several
+	 * hundred kilobytes are not worth complex detection what memory gets
+	 * clobbered. Moreover, on machines with SandyBridge graphics or in
+	 * setups that use crashkernel the entire 1M is reserved anyway.
 	 */
-	trim_snb_memory();
+	reserve_real_mode();
 
 	init_mem_mapping();
 
@@ -1226,6 +1234,14 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.timers.wallclock_init();
 
+	/*
+	 * This needs to run before setup_local_APIC() which soft-disables the
+	 * local APIC temporarily and that masks the thermal LVT interrupt,
+	 * leading to softlockups on machines which have configured SMI
+	 * interrupt delivery.
+	 */
+	therm_lvt_init();
+
 	mcheck_init();
 
 	register_refined_jiffies(CLOCK_TICK_RATE);