Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index a0854f2..af64519 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 1995 Linus Torvalds
*
@@ -52,8 +53,9 @@
#include <asm/switch_to.h>
#include <asm/xen/hypervisor.h>
#include <asm/vdso.h>
-#include <asm/intel_rdt_sched.h>
+#include <asm/resctrl_sched.h>
#include <asm/unistd.h>
+#include <asm/fsgsbase.h>
#ifdef CONFIG_IA32_EMULATION
/* Not included via unistd.h */
#include <asm/unistd_32_ia32.h>
@@ -61,15 +63,13 @@
#include "process.h"
-__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
-
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
unsigned long d0, d1, d2, d3, d6, d7;
unsigned int fsindex, gsindex;
- unsigned int ds, cs, es;
+ unsigned int ds, es;
show_iret_regs(regs);
@@ -101,7 +101,6 @@
}
asm("movl %%ds,%0" : "=r" (ds));
- asm("movl %%cs,%0" : "=r" (cs));
asm("movl %%es,%0" : "=r" (es));
asm("movl %%fs,%0" : "=r" (fsindex));
asm("movl %%gs,%0" : "=r" (gsindex));
@@ -117,7 +116,7 @@
printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
fs, fsindex, gs, gsindex, shadowgs);
- printk(KERN_DEFAULT "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
+ printk(KERN_DEFAULT "CS: %04lx DS: %04x ES: %04x CR0: %016lx\n", regs->cs, ds,
es, cr0);
printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
cr4);
@@ -144,17 +143,7 @@
void release_thread(struct task_struct *dead_task)
{
- if (dead_task->mm) {
-#ifdef CONFIG_MODIFY_LDT_SYSCALL
- if (dead_task->mm->context.ldt) {
- pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
- dead_task->comm,
- dead_task->mm->context.ldt->entries,
- dead_task->mm->context.ldt->nr_entries);
- BUG();
- }
-#endif
- }
+ WARN_ON(dead_task->mm);
}
enum which_selector {
@@ -288,6 +277,100 @@
}
}
+static __always_inline void x86_fsgsbase_load(struct thread_struct *prev,
+ struct thread_struct *next)
+{
+ load_seg_legacy(prev->fsindex, prev->fsbase,
+ next->fsindex, next->fsbase, FS);
+ load_seg_legacy(prev->gsindex, prev->gsbase,
+ next->gsindex, next->gsbase, GS);
+}
+
+static unsigned long x86_fsgsbase_read_task(struct task_struct *task,
+ unsigned short selector)
+{
+ unsigned short idx = selector >> 3;
+ unsigned long base;
+
+ if (likely((selector & SEGMENT_TI_MASK) == 0)) {
+ if (unlikely(idx >= GDT_ENTRIES))
+ return 0;
+
+ /*
+ * There are no user segments in the GDT with nonzero bases
+ * other than the TLS segments.
+ */
+ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+ return 0;
+
+ idx -= GDT_ENTRY_TLS_MIN;
+ base = get_desc_base(&task->thread.tls_array[idx]);
+ } else {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ struct ldt_struct *ldt;
+
+ /*
+ * If performance here mattered, we could protect the LDT
+ * with RCU. This is a slow path, though, so we can just
+ * take the mutex.
+ */
+ mutex_lock(&task->mm->context.lock);
+ ldt = task->mm->context.ldt;
+ if (unlikely(idx >= ldt->nr_entries))
+ base = 0;
+ else
+ base = get_desc_base(ldt->entries + idx);
+ mutex_unlock(&task->mm->context.lock);
+#else
+ base = 0;
+#endif
+ }
+
+ return base;
+}
+
+unsigned long x86_fsbase_read_task(struct task_struct *task)
+{
+ unsigned long fsbase;
+
+ if (task == current)
+ fsbase = x86_fsbase_read_cpu();
+ else if (task->thread.fsindex == 0)
+ fsbase = task->thread.fsbase;
+ else
+ fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex);
+
+ return fsbase;
+}
+
+unsigned long x86_gsbase_read_task(struct task_struct *task)
+{
+ unsigned long gsbase;
+
+ if (task == current)
+ gsbase = x86_gsbase_read_cpu_inactive();
+ else if (task->thread.gsindex == 0)
+ gsbase = task->thread.gsbase;
+ else
+ gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex);
+
+ return gsbase;
+}
+
+void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase)
+{
+ WARN_ON_ONCE(task == current);
+
+ task->thread.fsbase = fsbase;
+}
+
+void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase)
+{
+ WARN_ON_ONCE(task == current);
+
+ task->thread.gsbase = gsbase;
+}
+
int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
unsigned long arg, struct task_struct *p, unsigned long tls)
{
@@ -300,6 +383,7 @@
childregs = task_pt_regs(p);
fork_frame = container_of(childregs, struct fork_frame, regs);
frame = &fork_frame->frame;
+
frame->bp = 0;
frame->ret_addr = (unsigned long) ret_from_fork;
p->thread.sp = (unsigned long) fork_frame;
@@ -428,7 +512,8 @@
WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
this_cpu_read(irq_count) != -1);
- switch_fpu_prepare(prev_fpu, cpu);
+ if (!test_thread_flag(TIF_NEED_FPU_LOAD))
+ switch_fpu_prepare(prev_fpu, cpu);
/* We must save %fs and %gs before load_TLS() because
* %fs and %gs may be cleared by load_TLS().
@@ -446,9 +531,7 @@
/*
* Leave lazy mode, flushing any hypercalls made here. This
* must be done after loading TLS entries in the GDT but before
- * loading segments that might reference them, and and it must
- * be done before fpu__restore(), so the TS bit is up to
- * date.
+ * loading segments that might reference them.
*/
arch_end_context_switch(next_p);
@@ -474,12 +557,7 @@
if (unlikely(next->ds | prev->ds))
loadsegment(ds, next->ds);
- load_seg_legacy(prev->fsindex, prev->fsbase,
- next->fsindex, next->fsbase, FS);
- load_seg_legacy(prev->gsindex, prev->gsbase,
- next->gsindex, next->gsbase, GS);
-
- switch_fpu_finish(next_fpu, cpu);
+ x86_fsgsbase_load(prev, next);
/*
* Switch the PDA and FPU contexts.
@@ -487,6 +565,8 @@
this_cpu_write(current_task, next_p);
this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
+ switch_fpu_finish(next_fpu);
+
/* Reload sp0. */
update_task_stack(next_p);
@@ -532,7 +612,7 @@
}
/* Load the Intel cache allocation PQR MSR. */
- intel_rdt_sched_in();
+ resctrl_sched_in();
return prev_p;
}
@@ -556,7 +636,7 @@
/* TBD: overwrites user setup. Should have two bits.
But 64bit processes have always behaved this way,
so it's not too bad. The main problem is just that
- 32bit childs are affected again. */
+ 32bit children are affected again. */
current->personality &= ~READ_IMPLIES_EXEC;
}
@@ -569,10 +649,10 @@
current->mm->context.ia32_compat = TIF_X32;
current->personality &= ~READ_IMPLIES_EXEC;
/*
- * in_compat_syscall() uses the presence of the x32 syscall bit
+ * in_32bit_syscall() uses the presence of the x32 syscall bit
* flag to determine compat status. The x86 mmap() code relies on
* the syscall bitness so set x32 syscall bit right here to make
- * in_compat_syscall() work during exec().
+ * in_32bit_syscall() work during exec().
*
* Pretend to come from a x32 execve.
*/
@@ -623,54 +703,74 @@
long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
{
int ret = 0;
- int doit = task == current;
- int cpu;
switch (option) {
- case ARCH_SET_GS:
- if (arg2 >= TASK_SIZE_MAX)
+ case ARCH_SET_GS: {
+ if (unlikely(arg2 >= TASK_SIZE_MAX))
return -EPERM;
- cpu = get_cpu();
- task->thread.gsindex = 0;
- task->thread.gsbase = arg2;
- if (doit) {
- load_gs_index(0);
- ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2);
- }
- put_cpu();
- break;
- case ARCH_SET_FS:
- /* Not strictly needed for fs, but do it for symmetry
- with gs */
- if (arg2 >= TASK_SIZE_MAX)
- return -EPERM;
- cpu = get_cpu();
- task->thread.fsindex = 0;
- task->thread.fsbase = arg2;
- if (doit) {
- /* set the selector to 0 to not confuse __switch_to */
- loadsegment(fs, 0);
- ret = wrmsrl_safe(MSR_FS_BASE, arg2);
- }
- put_cpu();
- break;
- case ARCH_GET_FS: {
- unsigned long base;
- if (doit)
- rdmsrl(MSR_FS_BASE, base);
- else
- base = task->thread.fsbase;
+ preempt_disable();
+ /*
+ * ARCH_SET_GS has always overwritten the index
+ * and the base. Zero is the most sensible value
+ * to put in the index, and is the only value that
+ * makes any sense if FSGSBASE is unavailable.
+ */
+ if (task == current) {
+ loadseg(GS, 0);
+ x86_gsbase_write_cpu_inactive(arg2);
+
+ /*
+ * On non-FSGSBASE systems, save_base_legacy() expects
+ * that we also fill in thread.gsbase.
+ */
+ task->thread.gsbase = arg2;
+
+ } else {
+ task->thread.gsindex = 0;
+ x86_gsbase_write_task(task, arg2);
+ }
+ preempt_enable();
+ break;
+ }
+ case ARCH_SET_FS: {
+ /*
+ * Not strictly needed for %fs, but do it for symmetry
+ * with %gs
+ */
+ if (unlikely(arg2 >= TASK_SIZE_MAX))
+ return -EPERM;
+
+ preempt_disable();
+ /*
+ * Set the selector to 0 for the same reason
+ * as %gs above.
+ */
+ if (task == current) {
+ loadseg(FS, 0);
+ x86_fsbase_write_cpu(arg2);
+
+ /*
+ * On non-FSGSBASE systems, save_base_legacy() expects
+ * that we also fill in thread.fsbase.
+ */
+ task->thread.fsbase = arg2;
+ } else {
+ task->thread.fsindex = 0;
+ x86_fsbase_write_task(task, arg2);
+ }
+ preempt_enable();
+ break;
+ }
+ case ARCH_GET_FS: {
+ unsigned long base = x86_fsbase_read_task(task);
+
ret = put_user(base, (unsigned long __user *)arg2);
break;
}
case ARCH_GET_GS: {
- unsigned long base;
+ unsigned long base = x86_gsbase_read_task(task);
- if (doit)
- rdmsrl(MSR_KERNEL_GS_BASE, base);
- else
- base = task->thread.gsbase;
ret = put_user(base, (unsigned long __user *)arg2);
break;
}