Commit 6c9b7d79 authored by Thomas Gleixner's avatar Thomas Gleixner Committed by Borislav Petkov
Browse files

x86/tlb: Move PCID helpers where they are used



Aside of the fact that they are used only in the TLB code, especially
having the comment close to the actual implementation makes a lot of
sense.

Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Signed-off-by: default avatarBorislav Petkov <bp@suse.de>
Reviewed-by: default avatarAlexandre Chartre <alexandre.chartre@oracle.com>
Acked-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200421092600.145772183@linutronix.de
parent af5c40c6
Loading
Loading
Loading
Loading
+6 −127
Original line number Diff line number Diff line
@@ -13,133 +13,6 @@
#include <asm/pti.h>
#include <asm/processor-flags.h>

/*
 * The x86 feature is called PCID (Process Context IDentifier). It is similar
 * to what is traditionally called ASID on the RISC processors.
 *
 * We don't use the traditional ASID implementation, where each process/mm gets
 * its own ASID and flush/restart when we run out of ASID space.
 *
 * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
 * that came by on this CPU, allowing cheaper switch_mm between processes on
 * this CPU.
 *
 * We end up with different spaces for different things. To avoid confusion we
 * use different names for each of them:
 *
 * ASID  - [0, TLB_NR_DYN_ASIDS-1]
 *         the canonical identifier for an mm
 *
 * kPCID - [1, TLB_NR_DYN_ASIDS]
 *         the value we write into the PCID part of CR3; corresponds to the
 *         ASID+1, because PCID 0 is special.
 *
 * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
 *         for KPTI each mm has two address spaces and thus needs two
 *         PCID values, but we can still do with a single ASID denomination
 *         for each mm. Corresponds to kPCID + 2048.
 *
 */

/* There are 12 bits of space for ASIDS in CR3 */
#define CR3_HW_ASID_BITS		12

/*
 * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
 * user/kernel switches
 */
#ifdef CONFIG_PAGE_TABLE_ISOLATION
# define PTI_CONSUMED_PCID_BITS	1
#else
# define PTI_CONSUMED_PCID_BITS	0
#endif

#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)

/*
 * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
 * for them being zero-based.  Another -1 is because PCID 0 is reserved for
 * use by non-PCID-aware users.
 */
#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)

/*
 * 6 because 6 should be plenty and struct tlb_state will fit in two cache
 * lines.
 */
#define TLB_NR_DYN_ASIDS	6

/*
 * Given @asid, compute kPCID
 */
static inline u16 kern_pcid(u16 asid)
{
	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);

#ifdef CONFIG_PAGE_TABLE_ISOLATION
	/*
	 * Make sure that the dynamic ASID space does not confict with the
	 * bit we are using to switch between user and kernel ASIDs.
	 */
	BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));

	/*
	 * The ASID being passed in here should have respected the
	 * MAX_ASID_AVAILABLE and thus never have the switch bit set.
	 */
	VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
#endif
	/*
	 * The dynamically-assigned ASIDs that get passed in are small
	 * (<TLB_NR_DYN_ASIDS).  They never have the high switch bit set,
	 * so do not bother to clear it.
	 *
	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
	 * PCID bits.  This serves two purposes.  It prevents a nasty
	 * situation in which PCID-unaware code saves CR3, loads some other
	 * value (with PCID == 0), and then restores CR3, thus corrupting
	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
	 * that any bugs involving loading a PCID-enabled CR3 with
	 * CR4.PCIDE off will trigger deterministically.
	 */
	return asid + 1;
}

/*
 * Given @asid, compute uPCID
 */
static inline u16 user_pcid(u16 asid)
{
	u16 ret = kern_pcid(asid);
#ifdef CONFIG_PAGE_TABLE_ISOLATION
	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
#endif
	return ret;
}

struct pgd_t;
static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
{
	if (static_cpu_has(X86_FEATURE_PCID)) {
		return __sme_pa(pgd) | kern_pcid(asid);
	} else {
		VM_WARN_ON_ONCE(asid != 0);
		return __sme_pa(pgd);
	}
}

static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
{
	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
	/*
	 * Use boot_cpu_has() instead of this_cpu_has() as this function
	 * might be called during early boot. This should work even after
	 * boot because all CPU's the have same capabilities:
	 */
	VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID));
	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
}

struct flush_tlb_info;

void __flush_tlb_all(void);
@@ -153,6 +26,12 @@ void flush_tlb_others(const struct cpumask *cpumask,
#include <asm/paravirt.h>
#endif

/*
 * 6 because 6 should be plenty and struct tlb_state will fit in two cache
 * lines.
 */
#define TLB_NR_DYN_ASIDS	6

struct tlb_context {
	u64 ctx_id;
	u64 tlb_gen;
+120 −0
Original line number Diff line number Diff line
@@ -48,6 +48,126 @@
 */
#define LAST_USER_MM_IBPB	0x1UL

/*
 * The x86 feature is called PCID (Process Context IDentifier). It is similar
 * to what is traditionally called ASID on the RISC processors.
 *
 * We don't use the traditional ASID implementation, where each process/mm gets
 * its own ASID and flush/restart when we run out of ASID space.
 *
 * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
 * that came by on this CPU, allowing cheaper switch_mm between processes on
 * this CPU.
 *
 * We end up with different spaces for different things. To avoid confusion we
 * use different names for each of them:
 *
 * ASID  - [0, TLB_NR_DYN_ASIDS-1]
 *         the canonical identifier for an mm
 *
 * kPCID - [1, TLB_NR_DYN_ASIDS]
 *         the value we write into the PCID part of CR3; corresponds to the
 *         ASID+1, because PCID 0 is special.
 *
 * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
 *         for KPTI each mm has two address spaces and thus needs two
 *         PCID values, but we can still do with a single ASID denomination
 *         for each mm. Corresponds to kPCID + 2048.
 *
 */

/* There are 12 bits of space for ASIDS in CR3 */
#define CR3_HW_ASID_BITS		12

/*
 * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
 * user/kernel switches
 */
#ifdef CONFIG_PAGE_TABLE_ISOLATION
# define PTI_CONSUMED_PCID_BITS	1
#else
# define PTI_CONSUMED_PCID_BITS	0
#endif

#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)

/*
 * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
 * for them being zero-based.  Another -1 is because PCID 0 is reserved for
 * use by non-PCID-aware users.
 */
#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)

/*
 * Given @asid, compute kPCID
 */
static inline u16 kern_pcid(u16 asid)
{
	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);

#ifdef CONFIG_PAGE_TABLE_ISOLATION
	/*
	 * Make sure that the dynamic ASID space does not confict with the
	 * bit we are using to switch between user and kernel ASIDs.
	 */
	BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));

	/*
	 * The ASID being passed in here should have respected the
	 * MAX_ASID_AVAILABLE and thus never have the switch bit set.
	 */
	VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
#endif
	/*
	 * The dynamically-assigned ASIDs that get passed in are small
	 * (<TLB_NR_DYN_ASIDS).  They never have the high switch bit set,
	 * so do not bother to clear it.
	 *
	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
	 * PCID bits.  This serves two purposes.  It prevents a nasty
	 * situation in which PCID-unaware code saves CR3, loads some other
	 * value (with PCID == 0), and then restores CR3, thus corrupting
	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
	 * that any bugs involving loading a PCID-enabled CR3 with
	 * CR4.PCIDE off will trigger deterministically.
	 */
	return asid + 1;
}

/*
 * Given @asid, compute uPCID
 */
static inline u16 user_pcid(u16 asid)
{
	u16 ret = kern_pcid(asid);
#ifdef CONFIG_PAGE_TABLE_ISOLATION
	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
#endif
	return ret;
}

static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
{
	if (static_cpu_has(X86_FEATURE_PCID)) {
		return __sme_pa(pgd) | kern_pcid(asid);
	} else {
		VM_WARN_ON_ONCE(asid != 0);
		return __sme_pa(pgd);
	}
}

static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
{
	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
	/*
	 * Use boot_cpu_has() instead of this_cpu_has() as this function
	 * might be called during early boot. This should work even after
	 * boot because all CPU's the have same capabilities:
	 */
	VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID));
	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
}

/*
 * We get here when we do something requiring a TLB invalidation
 * but could not go invalidate all of the contexts.  We do the