Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "Apart from some new arm64 features and clean-ups, this also contains
  the core mmu_gather changes for tracking the levels of the page table
  being cleared and a minor update to the generic
  compat_sys_sigaltstack() introducing COMPAT_SIGMINSKSZ.

  Summary:

   - Core mmu_gather changes which allow tracking the levels of
     page-table being cleared together with the arm64 low-level flushing
     routines

   - Support for the new ARMv8.5 PSTATE.SSBS bit which can be used to
     mitigate Spectre-v4 dynamically without trapping to EL3 firmware

   - Introduce COMPAT_SIGMINSTKSZ for use in compat_sys_sigaltstack

   - Optimise emulation of MRS instructions to ID_* registers on ARMv8.4

   - Support for Common Not Private (CnP) translations allowing threads
     of the same CPU to share the TLB entries

   - Accelerated crc32 routines

   - Move swapper_pg_dir to the rodata section

   - Trap WFI instruction executed in user space

   - ARM erratum 1188874 workaround (arch_timer)

   - Miscellaneous fixes and clean-ups"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (78 commits)
  arm64: KVM: Guests can skip __install_bp_hardening_cb()s HYP work
  arm64: cpufeature: Trap CTR_EL0 access only where it is necessary
  arm64: cpufeature: Fix handling of CTR_EL0.IDC field
  arm64: cpufeature: ctr: Fix cpu capability check for late CPUs
  Documentation/arm64: HugeTLB page implementation
  arm64: mm: Use __pa_symbol() for set_swapper_pgd()
  arm64: Add silicon-errata.txt entry for ARM erratum 1188873
  Revert "arm64: uaccess: implement unsafe accessors"
  arm64: mm: Drop the unused cpu parameter
  MAINTAINERS: fix bad sdei paths
  arm64: mm: Use #ifdef for the __PAGETABLE_P?D_FOLDED defines
  arm64: Fix typo in a comment in arch/arm64/mm/kasan_init.c
  arm64: xen: Use existing helper to check interrupt status
  arm64: Use daifflag_restore after bp_hardening
  arm64: daifflags: Use irqflags functions for daifflags
  arm64: arch_timer: avoid unused function warning
  arm64: Trap WFI executed in userspace
  arm64: docs: Document SSBS HWCAP
  arm64: docs: Fix typos in ELF hwcaps
  arm64/kprobes: remove an extra semicolon in arch_prepare_kprobe
  ...

2 files changed, 77 insertions, 12 deletions

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index b3353e21f3b3..6be86c1c5c58 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -20,6 +20,8 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
+#ifdef CONFIG_MMU
+
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 /*
  * Semi RCU freeing of the page directories.
@@ -97,12 +99,30 @@ struct mmu_gather {
 #endif
 	unsigned long		start;
 	unsigned long		end;
-	/* we are in the middle of an operation to clear
-	 * a full mm and can make some optimizations */
-	unsigned int		fullmm : 1,
-	/* we have performed an operation which
-	 * requires a complete flush of the tlb */
-				need_flush_all : 1;
+	/*
+	 * we are in the middle of an operation to clear
+	 * a full mm and can make some optimizations
+	 */
+	unsigned int		fullmm : 1;
+
+	/*
+	 * we have performed an operation which
+	 * requires a complete flush of the tlb
+	 */
+	unsigned int		need_flush_all : 1;
+
+	/*
+	 * we have removed page directories
+	 */
+	unsigned int		freed_tables : 1;
+
+	/*
+	 * at which levels have we cleared entries?
+	 */
+	unsigned int		cleared_ptes : 1;
+	unsigned int		cleared_pmds : 1;
+	unsigned int		cleared_puds : 1;
+	unsigned int		cleared_p4ds : 1;
 
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
@@ -118,6 +138,7 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb,
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 			 unsigned long start, unsigned long end, bool force);
+void tlb_flush_mmu_free(struct mmu_gather *tlb);
 extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 				   int page_size);
 
@@ -137,6 +158,11 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 		tlb->start = TASK_SIZE;
 		tlb->end = 0;
 	}
+	tlb->freed_tables = 0;
+	tlb->cleared_ptes = 0;
+	tlb->cleared_pmds = 0;
+	tlb->cleared_puds = 0;
+	tlb->cleared_p4ds = 0;
 }
 
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
@@ -186,6 +212,25 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 }
 #endif
 
+static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
+{
+	if (tlb->cleared_ptes)
+		return PAGE_SHIFT;
+	if (tlb->cleared_pmds)
+		return PMD_SHIFT;
+	if (tlb->cleared_puds)
+		return PUD_SHIFT;
+	if (tlb->cleared_p4ds)
+		return P4D_SHIFT;
+
+	return PAGE_SHIFT;
+}
+
+static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
+{
+	return 1UL << tlb_get_unmap_shift(tlb);
+}
+
 /*
  * In the case of tlb vma handling, we can optimise these away in the
  * case where we're doing a full MM flush.  When we're doing a munmap,
@@ -219,13 +264,19 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->cleared_ptes = 1;				\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	     \
-	do {							     \
-		__tlb_adjust_range(tlb, address, huge_page_size(h)); \
-		__tlb_remove_tlb_entry(tlb, ptep, address);	     \
+#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
+	do {							\
+		unsigned long _sz = huge_page_size(h);		\
+		__tlb_adjust_range(tlb, address, _sz);		\
+		if (_sz == PMD_SIZE)				\
+			tlb->cleared_pmds = 1;			\
+		else if (_sz == PUD_SIZE)			\
+			tlb->cleared_puds = 1;			\
+		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
 /**
@@ -239,6 +290,7 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)			\
 	do {								\
 		__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE);	\
+		tlb->cleared_pmds = 1;					\
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);		\
 	} while (0)
 
@@ -253,6 +305,7 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #define tlb_remove_pud_tlb_entry(tlb, pudp, address)			\
 	do {								\
 		__tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE);	\
+		tlb->cleared_puds = 1;					\
 		__tlb_remove_pud_tlb_entry(tlb, pudp, address);		\
 	} while (0)
 
@@ -278,6 +331,8 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;				\
+		tlb->cleared_pmds = 1;				\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 #endif
@@ -285,7 +340,9 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;				\
+		tlb->cleared_puds = 1;				\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 #endif
@@ -295,6 +352,8 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;				\
+		tlb->cleared_p4ds = 1;				\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
@@ -304,12 +363,15 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 #ifndef p4d_free_tlb
 #define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;				\
 		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
 #endif
 
+#endif /* CONFIG_MMU */
+
 #define tlb_migrate_finish(mm) do {} while (0)
 
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 1a3c4f37e908..de0c13bdcd2c 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -103,6 +103,9 @@ typedef struct compat_sigaltstack {
 	compat_size_t			ss_size;
 } compat_stack_t;
 #endif
+#ifndef COMPAT_MINSIGSTKSZ
+#define COMPAT_MINSIGSTKSZ	MINSIGSTKSZ
+#endif
 
 #define compat_jiffies_to_clock_t(x)	\
 		(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)