From d52888aa2753e3063a9d3a0c9f72f94aa9809c15 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 26 Oct 2018 15:28:54 +0300 Subject: x86/mm: Move LDT remap out of KASLR region on 5-level paging On 5-level paging the LDT remap area is placed in the middle of the KASLR randomization region and it can overlap with the direct mapping, the vmalloc or the vmap area. The LDT mapping is per mm, so it cannot be moved into the P4D page table next to the CPU_ENTRY_AREA without complicating PGD table allocation for 5-level paging. The 4 PGD slot gap just before the direct mapping is reserved for hypervisors, so it cannot be used. Move the direct mapping one slot deeper and use the resulting gap for the LDT remap area. The resulting layout is the same for 4 and 5 level paging. [ tglx: Massaged changelog ] Fixes: f55f0501cbf6 ("x86/pti: Put the LDT in its own PGD if PTI is on") Signed-off-by: Kirill A. Shutemov Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Cc: bp@alien8.de Cc: hpa@zytor.com Cc: dave.hansen@linux.intel.com Cc: peterz@infradead.org Cc: boris.ostrovsky@oracle.com Cc: jgross@suse.com Cc: bhe@redhat.com Cc: willy@infradead.org Cc: linux-mm@kvack.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181026122856.66224-2-kirill.shutemov@linux.intel.com --- arch/x86/xen/mmu_pv.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86/xen') diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 0d7b3ae4960b..a5d7ed125337 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) init_top_pgt[0] = __pgd(0); /* Pre-constructed entries are in pfn, so convert to mfn */ - /* L4[272] -> level3_ident_pgt */ + /* L4[273] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ convert_pfn_mfn(init_top_pgt); @@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[0] = (unsigned long)pgd; addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; - /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][510] have entries that point to the same + /* Graft it onto L4[273][0]. Note that we creating an aliasing problem: + * Both L4[273][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you -- cgit v1.2.3 From 1457d8cf7664f34c4ba534c1073821a559a2f6f9 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 7 Nov 2018 18:01:00 +0100 Subject: x86/xen: fix pv boot Commit 9da3f2b7405440 ("x86/fault: BUG() when uaccess helpers fault on kernel addresses") introduced a regression for booting Xen PV guests. Xen PV guests are using __put_user() and __get_user() for accessing the p2m map (physical to machine frame number map) as accesses might fail in case of not populated areas of the map. With above commit using __put_user() and __get_user() for accessing kernel pages is no longer valid. So replace the Xen hack by adding appropriate p2m access functions using the default fixup handler. Fixes: 9da3f2b7405440 ("x86/fault: BUG() when uaccess helpers fault on kernel addresses") Signed-off-by: Juergen Gross Reviewed-by: Andrew Cooper Signed-off-by: Juergen Gross --- arch/x86/xen/p2m.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/x86/xen') diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index d6d74efd8912..4fe84436d5a7 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) /* * The interface requires atomic updates on p2m elements. - * xen_safe_write_ulong() is using __put_user which does an atomic - * store via asm(). + * xen_safe_write_ulong() is using an atomic store via asm(). */ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn))) return true; -- cgit v1.2.3 From d3132b3860f6cf35ff7609a76bbcdbb814bd027c Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 8 Nov 2018 08:35:06 +0100 Subject: xen: fix xen_qlock_wait() Commit a856531951dc80 ("xen: make xen_qlock_wait() nestable") introduced a regression for Xen guests running fully virtualized (HVM or PVH mode). The Xen hypervisor wouldn't return from the poll hypercall with interrupts disabled in case of an interrupt (for PV guests it does). So instead of disabling interrupts in xen_qlock_wait() use a nesting counter to avoid calling xen_clear_irq_pending() in case xen_qlock_wait() is nested. Fixes: a856531951dc80 ("xen: make xen_qlock_wait() nestable") Cc: stable@vger.kernel.org Reported-by: Sander Eikelenboom Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Tested-by: Sander Eikelenboom Signed-off-by: Juergen Gross --- arch/x86/xen/spinlock.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'arch/x86/xen') diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 441c88262169..1c8a8816a402 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -21,6 +22,7 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(char *, irq_name); +static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest); static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) @@ -39,25 +41,25 @@ static void xen_qlock_kick(int cpu) */ static void xen_qlock_wait(u8 *byte, u8 val) { - unsigned long flags; int irq = __this_cpu_read(lock_kicker_irq); + atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest); /* If kicker interrupts not initialized yet, just spin */ if (irq == -1 || in_nmi()) return; - /* Guard against reentry. */ - local_irq_save(flags); + /* Detect reentry. */ + atomic_inc(nest_cnt); - /* If irq pending already clear it. */ - if (xen_test_irq_pending(irq)) { + /* If irq pending already and no nested call clear it. */ + if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) { xen_clear_irq_pending(irq); } else if (READ_ONCE(*byte) == val) { /* Block until irq becomes pending (or a spurious wakeup) */ xen_poll_irq(irq); } - local_irq_restore(flags); + atomic_dec(nest_cnt); } static irqreturn_t dummy_handler(int irq, void *dev_id) -- cgit v1.2.3