On Mon, Nov 19, 2018 at 12:24:36PM +0000, gregkh@xxxxxxxxxxxxxxxxxxx wrote:
>
> The patch below does not apply to the 4.14-stable tree.
> If someone wants it applied there, or to any other stable or longterm
> tree, then please email the backport, including the original git commit
> id to <stable@xxxxxxxxxxxxxxx>.
>From 4d5b6e1f7425e22ff1ac055e55e15c4f104af4e5 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Date: Fri, 26 Oct 2018 15:28:55 +0300
Subject: [PATCH 2/2] x86/ldt: Unmap PTEs for the slot before freeing LDT pages
commit a0e6e0831c516860fc7f9be1db6c081fe902ebcf upstream
modify_ldt(2) leaves the old LDT mapped after switching over to the new
one. The old LDT gets freed and the pages can be re-used.
Leaving the mapping in place can have security implications. The mapping is
present in the userspace page tables and Meltdown-like attacks can read
these freed and possibly reused pages.
It's relatively simple to fix: unmap the old LDT and flush TLB before
freeing the old LDT memory.
This further allows to avoid flushing the TLB in map_ldt_struct() as the
slot is unmapped and flushed by unmap_ldt_struct() or has never been mapped
at all.
[ tglx: Massaged changelog and removed the needless line breaks ]
Fixes: f55f0501cbf6 ("x86/pti: Put the LDT in its own PGD if PTI is on")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: bp@xxxxxxxxx
Cc: hpa@xxxxxxxxx
Cc: dave.hansen@xxxxxxxxxxxxxxx
Cc: luto@xxxxxxxxxx
Cc: peterz@xxxxxxxxxxxxx
Cc: boris.ostrovsky@xxxxxxxxxx
Cc: jgross@xxxxxxxx
Cc: bhe@xxxxxxxxxx
Cc: willy@xxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Cc: stable@xxxxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/20181026122856.66224-3-kirill.shutemov@xxxxxxxxxxxxxxx
---
arch/x86/kernel/ldt.c | 49 +++++++++++++++++++++++++++++++------------
1 file changed, 36 insertions(+), 13 deletions(-)
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 26d713ecad34..65df298d4e9e 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -103,14 +103,6 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
/*
* If PTI is enabled, this maps the LDT into the kernelmode and
* usermode tables for the given mm.
- *
- * There is no corresponding unmap function. Even if the LDT is freed, we
- * leave the PTEs around until the slot is reused or the mm is destroyed.
- * This is harmless: the LDT is always in ordinary memory, and no one will
- * access the freed slot.
- *
- * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
- * it useful, and the flush would slow down modify_ldt().
*/
static int
map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
@@ -119,8 +111,8 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
bool is_vmalloc, had_top_level_entry;
unsigned long va;
spinlock_t *ptl;
+ int i, nr_pages;
pgd_t *pgd;
- int i;
if (!static_cpu_has(X86_FEATURE_PTI))
return 0;
@@ -141,7 +133,9 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
is_vmalloc = is_vmalloc_addr(ldt->entries);
- for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+ nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
+
+ for (i = 0; i < nr_pages; i++) {
unsigned long offset = i << PAGE_SHIFT;
const void *src = (char *)ldt->entries + offset;
unsigned long pfn;
@@ -189,14 +183,42 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
}
}
- va = (unsigned long)ldt_slot_va(slot);
- flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
-
ldt->slot = slot;
#endif
return 0;
}
+static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ unsigned long va;
+ int i, nr_pages;
+
+ if (!ldt)
+ return;
+
+ /* LDT map/unmap is only required for PTI */
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
+
+ for (i = 0; i < nr_pages; i++) {
+ unsigned long offset = i << PAGE_SHIFT;
+ spinlock_t *ptl;
+ pte_t *ptep;
+
+ va = (unsigned long)ldt_slot_va(ldt->slot) + offset;
+ ptep = get_locked_pte(mm, va, &ptl);
+ pte_clear(mm, va, ptep);
+ pte_unmap_unlock(ptep, ptl);
+ }
+
+ va = (unsigned long)ldt_slot_va(ldt->slot);
+ flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, 0);
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+}
+
static void free_ldt_pgtables(struct mm_struct *mm)
{
#ifdef CONFIG_PAGE_TABLE_ISOLATION
@@ -433,6 +455,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
}
install_ldt(mm, new_ldt);
+ unmap_ldt_struct(mm, old_ldt);
free_ldt_struct(old_ldt);
error = 0;
--
Kirill A. Shutemov
