Merge tag 'x86-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core x86 updates from Ingo Molnar:

 - The biggest change is the rework of the percpu code, to support the
   'Named Address Spaces' GCC feature, by Uros Bizjak:

      - This allows C code to access GS and FS segment relative memory
        via variables declared with such attributes, which allows the
        compiler to better optimize those accesses than the previous
        inline assembly code.

      - The series also includes a number of micro-optimizations for
        various percpu access methods, plus a number of cleanups of %gs
        accesses in assembly code.

      - These changes have been exposed to linux-next testing for the
        last ~5 months, with no known regressions in this area.

 - Fix/clean up __switch_to()'s broken but accidentally working handling
   of FPU switching - which also generates better code

 - Propagate more RIP-relative addressing in assembly code, to generate
   slightly better code

 - Rework the CPU mitigations Kconfig space to be less idiosyncratic, to
   make it easier for distros to follow & maintain these options

 - Rework the x86 idle code to cure RCU violations and to clean up the
   logic

 - Clean up the vDSO Makefile logic

 - Misc cleanups and fixes

* tag 'x86-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
  x86/idle: Select idle routine only once
  x86/idle: Let prefer_mwait_c1_over_halt() return bool
  x86/idle: Cleanup idle_setup()
  x86/idle: Clean up idle selection
  x86/idle: Sanitize X86_BUG_AMD_E400 handling
  sched/idle: Conditionally handle tick broadcast in default_idle_call()
  x86: Increase brk randomness entropy for 64-bit systems
  x86/vdso: Move vDSO to mmap region
  x86/vdso/kbuild: Group non-standard build attributes and primary object file rules together
  x86/vdso: Fix rethunk patching for vdso-image-{32,64}.o
  x86/retpoline: Ensure default return thunk isn't used at runtime
  x86/vdso: Use CONFIG_COMPAT_32 to specify vdso32
  x86/vdso: Use $(addprefix ) instead of $(foreach )
  x86/vdso: Simplify obj-y addition
  x86/vdso: Consolidate targets and clean-files
  x86/bugs: Rename CONFIG_RETHUNK              => CONFIG_MITIGATION_RETHUNK
  x86/bugs: Rename CONFIG_CPU_SRSO             => CONFIG_MITIGATION_SRSO
  x86/bugs: Rename CONFIG_CPU_IBRS_ENTRY       => CONFIG_MITIGATION_IBRS_ENTRY
  x86/bugs: Rename CONFIG_CPU_UNRET_ENTRY      => CONFIG_MITIGATION_UNRET_ENTRY
  x86/bugs: Rename CONFIG_SLS                  => CONFIG_MITIGATION_SLS
  ...

1 files changed, 25 insertions, 7 deletions

diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index aeccea2da91b..30335182b6b0 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -24,6 +24,8 @@
 
 static int __initdata_or_module debug_callthunks;
 
+#define MAX_PATCH_LEN (255-1)
+
 #define prdbg(fmt, args...)					\
 do {								\
 	if (debug_callthunks)					\
@@ -179,10 +181,15 @@ static const u8 nops[] = {
 static void *patch_dest(void *dest, bool direct)
 {
 	unsigned int tsize = SKL_TMPL_SIZE;
+	u8 insn_buff[MAX_PATCH_LEN];
 	u8 *pad = dest - tsize;
 
+	memcpy(insn_buff, skl_call_thunk_template, tsize);
+	apply_relocation(insn_buff, tsize, pad,
+			 skl_call_thunk_template, tsize);
+
 	/* Already patched? */
-	if (!bcmp(pad, skl_call_thunk_template, tsize))
+	if (!bcmp(pad, insn_buff, tsize))
 		return pad;
 
 	/* Ensure there are nops */
@@ -192,9 +199,9 @@ static void *patch_dest(void *dest, bool direct)
 	}
 
 	if (direct)
-		memcpy(pad, skl_call_thunk_template, tsize);
+		memcpy(pad, insn_buff, tsize);
 	else
-		text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true);
+		text_poke_copy_locked(pad, insn_buff, tsize, true);
 	return pad;
 }
 
@@ -290,20 +297,27 @@ void *callthunks_translate_call_dest(void *dest)
 static bool is_callthunk(void *addr)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
-	void *tmpl = skl_call_thunk_template;
+	u8 insn_buff[MAX_PATCH_LEN];
 	unsigned long dest;
+	u8 *pad;
 
 	dest = roundup((unsigned long)addr, CONFIG_FUNCTION_ALIGNMENT);
 	if (!thunks_initialized || skip_addr((void *)dest))
 		return false;
 
-	return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size);
+	pad = (void *)(dest - tmpl_size);
+
+	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
+	apply_relocation(insn_buff, tmpl_size, pad,
+			 skl_call_thunk_template, tmpl_size);
+
+	return !bcmp(pad, insn_buff, tmpl_size);
 }
 
 int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
-	void *tmpl = skl_call_thunk_template;
+	u8 insn_buff[MAX_PATCH_LEN];
 
 	if (!thunks_initialized)
 		return 0;
@@ -312,7 +326,11 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 	if (func && is_callthunk(func))
 		return 0;
 
-	memcpy(*pprog, tmpl, tmpl_size);
+	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
+	apply_relocation(insn_buff, tmpl_size, *pprog,
+			 skl_call_thunk_template, tmpl_size);
+
+	memcpy(*pprog, insn_buff, tmpl_size);
 	*pprog += tmpl_size;
 	return tmpl_size;
 }