[PATCH AUTOSEL 5.4 24/73] x86/mm: Flush global TLB when switching to trampoline page-table

From: Sasha Levin
Date: Mon Jan 17 2022 - 22:13:46 EST


From: Joerg Roedel <jroedel@xxxxxxx>

[ Upstream commit 71d5049b053876afbde6c3273250b76935494ab2 ]

Move the switching code into a function so that it can be re-used and
add a global TLB flush. This makes sure that usage of memory which is
not mapped in the trampoline page-table is reliably caught.

Also move the clearing of CR4.PCIDE before the CR3 switch because the
cr4_clear_bits() function will access data not mapped into the
trampoline page-table.

Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Link: https://lore.kernel.org/r/20211202153226.22946-4-joro@xxxxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
arch/x86/include/asm/realmode.h | 1 +
arch/x86/kernel/reboot.c | 12 ++----------
arch/x86/realmode/init.c | 26 ++++++++++++++++++++++++++
3 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index 09ecc32f65248..52d7512ea91ab 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -82,6 +82,7 @@ static inline void set_real_mode_mem(phys_addr_t mem)
}

void reserve_real_mode(void);
+void load_trampoline_pgtable(void);

#endif /* __ASSEMBLY__ */

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index d65d1afb27161..fdef27a84d713 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -113,17 +113,9 @@ void __noreturn machine_real_restart(unsigned int type)
spin_unlock(&rtc_lock);

/*
- * Switch back to the initial page table.
+ * Switch to the trampoline page table.
*/
-#ifdef CONFIG_X86_32
- load_cr3(initial_page_table);
-#else
- write_cr3(real_mode_header->trampoline_pgd);
-
- /* Exiting long mode will fail if CR4.PCIDE is set. */
- if (boot_cpu_has(X86_FEATURE_PCID))
- cr4_clear_bits(X86_CR4_PCIDE);
-#endif
+ load_trampoline_pgtable();

/* Jump to the identity-mapped low memory code */
#ifdef CONFIG_X86_32
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index de371e52cfa85..fac50ebb122b5 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -16,6 +16,32 @@ u32 *trampoline_cr4_features;
/* Hold the pgd entry used on booting additional CPUs */
pgd_t trampoline_pgd_entry;

+void load_trampoline_pgtable(void)
+{
+#ifdef CONFIG_X86_32
+ load_cr3(initial_page_table);
+#else
+ /*
+ * This function is called before exiting to real-mode and that will
+ * fail with CR4.PCIDE still set.
+ */
+ if (boot_cpu_has(X86_FEATURE_PCID))
+ cr4_clear_bits(X86_CR4_PCIDE);
+
+ write_cr3(real_mode_header->trampoline_pgd);
+#endif
+
+ /*
+ * The CR3 write above will not flush global TLB entries.
+ * Stale, global entries from previous page tables may still be
+ * present. Flush those stale entries.
+ *
+ * This ensures that memory accessed while running with
+ * trampoline_pgd is *actually* mapped into trampoline_pgd.
+ */
+ __flush_tlb_all();
+}
+
void __init reserve_real_mode(void)
{
phys_addr_t mem;
--
2.34.1