linux/arch/x86/include/asm/mmu.h
Peter Zijlstra 7f9958230d x86/mm: Fix false positive warning in switch_mm_irqs_off()
Multiple testers reported the following new warning:

	WARNING: CPU: 0 PID: 0 at arch/x86/mm/tlb.c:795

Which corresponds to:

	if (IS_ENABLED(CONFIG_DEBUG_VM) && WARN_ON_ONCE(prev != &init_mm &&
	    !cpumask_test_cpu(cpu, mm_cpumask(next))))
		cpumask_set_cpu(cpu, mm_cpumask(next));

So the problem is that unuse_temporary_mm() explicitly clears
that bit; and it has to, because otherwise the flush_tlb_mm_range() in
__text_poke() will try sending IPIs, which are not at all needed.

See also:

   https://lore.kernel.org/all/20241113095550.GBZzR3pg-RhJKPDazS@fat_crate.local/

Notably, the whole {,un}use_temporary_mm() thing requires preemption to
be disabled across it with the express purpose of keeping all TLB
nonsense CPU local, such that invalidations can also stay local etc.

However, as a side-effect, we violate this above WARN(), which sorta
makes sense for the normal case, but very much doesn't make sense here.

Change unuse_temporary_mm() to mark the mm_struct such that a further
exception (beyond init_mm) can be grafted, to keep the warning for all
the other cases.

Reported-by: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Reported-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rik van Riel <riel@surriel.com>
Link: https://lore.kernel.org/r/20250430081154.GH4439@noisy.programming.kicks-ass.net
2025-05-06 11:28:57 +02:00

95 lines
2.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_MMU_H
#define _ASM_X86_MMU_H
#include <linux/spinlock.h>
#include <linux/rwsem.h>
#include <linux/mutex.h>
#include <linux/atomic.h>
#include <linux/bits.h>
/* Uprobes on this MM assume 32-bit code */
#define MM_CONTEXT_UPROBE_IA32 0
/* vsyscall page is accessible on this MM */
#define MM_CONTEXT_HAS_VSYSCALL 1
/* Do not allow changing LAM mode */
#define MM_CONTEXT_LOCK_LAM 2
/* Allow LAM and SVA coexisting */
#define MM_CONTEXT_FORCE_TAGGED_SVA 3
/* Tracks mm_cpumask */
#define MM_CONTEXT_NOTRACK 4
/*
* x86 has arch-specific MMU state beyond what lives in mm_struct.
*/
typedef struct {
/*
* ctx_id uniquely identifies this mm_struct. A ctx_id will never
* be reused, and zero is not a valid ctx_id.
*/
u64 ctx_id;
/*
* Any code that needs to do any sort of TLB flushing for this
* mm will first make its changes to the page tables, then
* increment tlb_gen, then flush. This lets the low-level
* flushing code keep track of what needs flushing.
*
* This is not used on Xen PV.
*/
atomic64_t tlb_gen;
unsigned long next_trim_cpumask;
#ifdef CONFIG_MODIFY_LDT_SYSCALL
struct rw_semaphore ldt_usr_sem;
struct ldt_struct *ldt;
#endif
unsigned long flags;
#ifdef CONFIG_ADDRESS_MASKING
/* Active LAM mode: X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */
unsigned long lam_cr3_mask;
/* Significant bits of the virtual address. Excludes tag bits. */
u64 untag_mask;
#endif
struct mutex lock;
void __user *vdso; /* vdso base address */
const struct vdso_image *vdso_image; /* vdso image in use */
atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
/*
* One bit per protection key says whether userspace can
* use it or not. protected by mmap_lock.
*/
u16 pkey_allocation_map;
s16 execute_only_pkey;
#endif
#ifdef CONFIG_BROADCAST_TLB_FLUSH
/*
* The global ASID will be a non-zero value when the process has
* the same ASID across all CPUs, allowing it to make use of
* hardware-assisted remote TLB invalidation like AMD INVLPGB.
*/
u16 global_asid;
/* The process is transitioning to a new global ASID number. */
bool asid_transition;
#endif
} mm_context_t;
#define INIT_MM_CONTEXT(mm) \
.context = { \
.ctx_id = 1, \
.lock = __MUTEX_INITIALIZER(mm.context.lock), \
}
void leave_mm(void);
#define leave_mm leave_mm
#endif /* _ASM_X86_MMU_H */