From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/arch/x86/kernel/ldt.c | 128 +++++++++++++++++++++++++++++++++++++++---
1 files changed, 117 insertions(+), 11 deletions(-)
diff --git a/kernel/arch/x86/kernel/ldt.c b/kernel/arch/x86/kernel/ldt.c
index 65590ee..b8aee71 100644
--- a/kernel/arch/x86/kernel/ldt.c
+++ b/kernel/arch/x86/kernel/ldt.c
@@ -8,7 +8,7 @@
*
* Lock order:
* contex.ldt_usr_sem
- * mmap_sem
+ * mmap_lock
* context.lock
*/
@@ -27,7 +27,91 @@
#include <asm/tlb.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
-#include <asm/syscalls.h>
+#include <asm/pgtable_areas.h>
+
+#include <xen/xen.h>
+
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+ return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+}
+
+void load_mm_ldt(struct mm_struct *mm)
+{
+ struct ldt_struct *ldt;
+
+ /* READ_ONCE synchronizes with smp_store_release */
+ ldt = READ_ONCE(mm->context.ldt);
+
+ /*
+ * Any change to mm->context.ldt is followed by an IPI to all
+ * CPUs with the mm active. The LDT will not be freed until
+ * after the IPI is handled by all such CPUs. This means that,
+ * if the ldt_struct changes before we return, the values we see
+ * will be safe, and the new values will be loaded before we run
+ * any user code.
+ *
+ * NB: don't try to convert this to use RCU without extreme care.
+ * We would still need IRQs off, because we don't want to change
+ * the local LDT after an IPI loaded a newer value than the one
+ * that we can see.
+ */
+
+ if (unlikely(ldt)) {
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+ /*
+ * Whoops -- either the new LDT isn't mapped
+ * (if slot == -1) or is mapped into a bogus
+ * slot (if slot > 1).
+ */
+ clear_LDT();
+ return;
+ }
+
+ /*
+ * If page table isolation is enabled, ldt->entries
+ * will not be mapped in the userspace pagetables.
+ * Tell the CPU to access the LDT through the alias
+ * at ldt_slot_va(ldt->slot).
+ */
+ set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+ } else {
+ set_ldt(ldt->entries, ldt->nr_entries);
+ }
+ } else {
+ clear_LDT();
+ }
+}
+
+void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
+{
+ /*
+ * Load the LDT if either the old or new mm had an LDT.
+ *
+ * An mm will never go from having an LDT to not having an LDT. Two
+ * mms never share an LDT, so we don't gain anything by checking to
+ * see whether the LDT changed. There's also no guarantee that
+ * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL,
+ * then prev->context.ldt will also be non-NULL.
+ *
+ * If we really cared, we could optimize the case where prev == next
+ * and we're exiting lazy mode. Most of the time, if this happens,
+ * we don't actually need to reload LDTR, but modify_ldt() is mostly
+ * used by legacy code and emulators where we don't need this level of
+ * performance.
+ *
+ * This uses | instead of || because it generates better code.
+ */
+ if (unlikely((unsigned long)prev->context.ldt |
+ (unsigned long)next->context.ldt))
+ load_mm_ldt(next);
+
+ DEBUG_LOCKS_WARN_ON(preemptible());
+}
static void refresh_ldt_segments(void)
{
@@ -113,7 +197,7 @@
* tables.
*/
WARN_ON(!had_kernel_mapping);
- if (static_cpu_has(X86_FEATURE_PTI))
+ if (boot_cpu_has(X86_FEATURE_PTI))
WARN_ON(!had_user_mapping);
} else {
/*
@@ -121,7 +205,7 @@
* Sync the pgd to the usermode tables.
*/
WARN_ON(had_kernel_mapping);
- if (static_cpu_has(X86_FEATURE_PTI))
+ if (boot_cpu_has(X86_FEATURE_PTI))
WARN_ON(had_user_mapping);
}
}
@@ -156,7 +240,7 @@
k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
- if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+ if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
set_pmd(u_pmd, *k_pmd);
}
@@ -181,7 +265,7 @@
{
pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
- if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+ if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
set_pgd(kernel_to_user_pgdp(pgd), *pgd);
}
@@ -208,7 +292,7 @@
spinlock_t *ptl;
int i, nr_pages;
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return 0;
/*
@@ -271,7 +355,7 @@
return;
/* LDT map/unmap is only required for PTI */
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return;
nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
@@ -288,7 +372,7 @@
}
va = (unsigned long)ldt_slot_va(ldt->slot);
- flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, 0);
+ flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false);
}
#else /* !CONFIG_PAGE_TABLE_ISOLATION */
@@ -311,7 +395,7 @@
unsigned long start = LDT_BASE_ADDR;
unsigned long end = LDT_END_ADDR;
- if (!static_cpu_has(X86_FEATURE_PTI))
+ if (!boot_cpu_has(X86_FEATURE_PTI))
return;
tlb_gather_mmu(&tlb, mm, start, end);
@@ -461,6 +545,28 @@
return bytecount;
}
+static bool allow_16bit_segments(void)
+{
+ if (!IS_ENABLED(CONFIG_X86_16BIT))
+ return false;
+
+#ifdef CONFIG_XEN_PV
+ /*
+ * Xen PV does not implement ESPFIX64, which means that 16-bit
+ * segments will not work correctly. Until either Xen PV implements
+ * ESPFIX64 and can signal this fact to the guest or unless someone
+ * provides compelling evidence that allowing broken 16-bit segments
+ * is worthwhile, disallow 16-bit segments under Xen PV.
+ */
+ if (xen_pv_domain()) {
+ pr_info_once("Warning: 16-bit segments do not work correctly in a Xen PV guest\n");
+ return false;
+ }
+#endif
+
+ return true;
+}
+
static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
{
struct mm_struct *mm = current->mm;
@@ -492,7 +598,7 @@
/* The user wants to clear the entry. */
memset(&ldt, 0, sizeof(ldt));
} else {
- if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+ if (!ldt_info.seg_32bit && !allow_16bit_segments()) {
error = -EINVAL;
goto out;
}
--
Gitblit v1.6.2