When an NMI hits in the #VC handler entry code before it has switched to
another stack, any subsequent #VC exception in the NMI code-path will
overwrite the interrupted #VC handler's stack.
Make sure this doesn't happen by explicitly adjusting the #VC IST entry
in the NMI handler for the time it can cause #VC exceptions.
[ bp: Touchups, spelling fixes. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-44-joro@8bytes.org
Allocate and map an IST stack and an additional fall-back stack for
the #VC handler. The memory for the stacks is allocated only when
SEV-ES is active.
The #VC handler needs to use an IST stack because a #VC exception can be
raised from kernel space with unsafe stack, e.g. in the SYSCALL entry
path.
Since the #VC exception can be nested, the #VC handler switches back to
the interrupted stack when entered from kernel space. If switching back
is not possible, the fall-back stack is used.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-43-joro@8bytes.org
Add the infrastructure to handle #VC exceptions when the kernel runs on
virtual addresses and has mapped a GHCB. This handler will be used until
the runtime #VC handler takes over.
Since the handler runs very early, disable instrumentation for sev-es.c.
[ bp: Make vc_ghcb_invalidate() __always_inline so that it can be
inlined in noinstr functions like __sev_es_nmi_complete(). ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200908123816.GB3764@8bytes.org
Setup an early handler for #VC exceptions. There is no GHCB mapped
yet, so just re-use the vc_no_ghcb_handler(). It can only handle
CPUID exit-codes, but that should be enough to get the kernel through
verify_cpu() and __startup_64() until it runs on virtual addresses.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
[ boot failure Error: kernel_ident_mapping_init() failed. ]
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lkml.kernel.org/r/20200908123517.GA3764@8bytes.org
Setup sev-es.c and include the code from the pre-decompression stage
to also build it into the image of the running kernel. Temporarily add
__maybe_unused annotations to avoid build warnings until the functions
get used.
[ bp: Use the non-tracing rd/wrmsr variants because:
vmlinux.o: warning: objtool: __sev_es_nmi_complete()+0x11f: \
call to do_trace_write_msr() leaves .noinstr.text section
as __sev_es_nmi_complete() is noinstr due to being called from the
NMI handler exc_nmi(). ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-39-joro@8bytes.org
Stop providing the possibility to override the address space using
set_fs() now that there is no need for that any more. To properly
handle the TASK_SIZE_MAX checking for 4 vs 5-level page tables on
x86 a new alternative is introduced, which just like the one in
entry_64.S has to use the hardcoded virtual address bits to escape
the fact that TASK_SIZE_MAX isn't actually a constant when 5-level
page tables are enabled.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Move the assembly coded dispatch between page-faults and all other
exceptions to C code to make it easier to maintain and extend.
Also change the return-type of early_make_pgtable() to bool and make it
static.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-36-joro@8bytes.org
Move these two functions from kernel/idt.c to include/asm/desc.h:
* init_idt_data()
* idt_init_desc()
These functions are needed to setup IDT entries very early and need to
be called from head64.c. To be usable this early, these functions need
to be compiled without instrumentation and the stack-protector feature.
These features need to be kept enabled for kernel/idt.c, so head64.c
must use its own versions.
[ bp: Take Kees' suggested patch title and add his Rev-by. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-35-joro@8bytes.org
Add a separate bringup IDT for the CPU bringup code that will be used
until the kernel switches to the idt_table. There are two reasons for a
separate IDT:
1) When the idt_table is set up and the secondary CPUs are
booted, it contains entries (e.g. IST entries) which
require certain CPU state to be set up. This includes a
working TSS (for IST), MSR_GS_BASE (for stack protector) or
CR4.FSGSBASE (for paranoid_entry) path. By using a
dedicated IDT for early boot this state need not to be set
up early.
2) The idt_table is static to idt.c, so any function
using/modifying must be in idt.c too. That means that all
compiler driven instrumentation like tracing or KASAN is
also active in this code. But during early CPU bringup the
environment is not set up for this instrumentation to work
correctly.
To avoid all of these hassles and make early exception handling robust,
use a dedicated bringup IDT.
The IDT is loaded two times, first on the boot CPU while the kernel is
still running on direct mapped addresses, and again later after the
switch to kernel addresses has happened. The second IDT load happens on
the boot and secondary CPUs.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-34-joro@8bytes.org
Make sure there is a stack once the kernel runs from virtual addresses.
At this stage any secondary CPU which boots will have lost its stack
because the kernel switched to a new page-table which does not map the
real-mode stack anymore.
This is needed for handling early #VC exceptions caused by instructions
like CPUID.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-33-joro@8bytes.org
The code to setup idt_data is needed for early exception handling, but
set_intr_gate() can't be used that early because it has pv-ops in its
code path which don't work that early.
Split out the idt_data initialization part from set_intr_gate() so
that it can be used separately.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200907131613.12703-29-joro@8bytes.org
Install an exception handler for #VC exception that uses a GHCB. Also
add the infrastructure for handling different exit-codes by decoding
the instruction that caused the exception and error handling.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-24-joro@8bytes.org
Add the first handler for #VC exceptions. At stage 1 there is no GHCB
yet because the kernel might still be running on the EFI page table.
The stage 1 handler is limited to the MSR-based protocol to talk to the
hypervisor and can only support CPUID exit-codes, but that is enough to
get to stage 2.
[ bp: Zap superfluous newlines after rd/wrmsr instruction mnemonics. ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200907131613.12703-20-joro@8bytes.org
Current usage of thread.debugreg6 is convoluted at best. It starts life as
a copy of the hardware DR6 value, but then various bits are cleared and
set.
Replace this with a new variable thread.virtual_dr6 that is initialized to
0 when DR6 is read and only gains bits, at the same time the actual (on
stack) dr6 value which is read from the hardware only gets bits cleared.
Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.415372940@infradead.org
DR6 has a whole bunch of bits that have negative polarity; they were
architecturally reserved and defined to be 1 and are now getting used.
Since they're 1 by default, 0 becomes the signal value.
Handle this by xor'ing the read DR6 value by the reserved mask, this
will flip them around such that 1 is the signal value (positive
polarity).
Current Linux doesn't yet support any of these bits, but there's two
defined:
- DR6[11] Bus Lock Debug Exception (ISEr39)
- DR6[16] Restricted Transactional Memory (SDM)
Update ptrace_{set,get}_debugreg() to provide/consume the value in
architectural polarity. Although afaict ptrace_set_debugreg(6) is
pointless, the value is not consumed anywhere.
Change hw_breakpoint_restore() to alway write the DR6_RESERVED value
to DR6, again, no consumer for that write.
Suggested-by: Andrew Cooper <Andrew.Cooper3@citrix.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20200902133201.354220797@infradead.org
We found that callers of dma_get_seg_boundary mostly do an ALIGN
with page mask and then do a page shift to get number of pages:
ALIGN(boundary + 1, 1 << shift) >> shift
However, the boundary might be as large as ULONG_MAX, which means
that a device has no specific boundary limit. So either "+ 1" or
passing it to ALIGN() would potentially overflow.
According to kernel defines:
#define ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
#define ALIGN(x, a) ALIGN_MASK(x, (typeof(x))(a) - 1)
We can simplify the logic here into a helper function doing:
ALIGN(boundary + 1, 1 << shift) >> shift
= ALIGN_MASK(b + 1, (1 << s) - 1) >> s
= {[b + 1 + (1 << s) - 1] & ~[(1 << s) - 1]} >> s
= [b + 1 + (1 << s) - 1] >> s
= [b + (1 << s)] >> s
= (b >> s) + 1
This patch introduces and applies dma_get_seg_boundary_nr_pages()
as an overflow-free helper for the dma_get_seg_boundary() callers
to get numbers of pages. It also takes care of the NULL dev case
for non-DMA API callers.
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Acked-by: Niklas Schnelle <schnelle@linux.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Signed-off-by: Christoph Hellwig <hch@lst.de>
In order to use static_call() to wire up x86_pmu, we need to
initialize earlier, specifically before memory allocation works; copy
some of the tricks from jump_label to enable this.
Primarily we overload key->next to store a sites pointer when there
are no modules, this avoids having to use kmalloc() to initialize the
sites and allows us to run much earlier.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20200818135805.220737930@infradead.org
Extend the static_call infrastructure to optimize the following common
pattern:
if (func_ptr)
func_ptr(args...)
For the trampoline (which is in effect a tail-call), we patch the
JMP.d32 into a RET, which then directly consumes the trampoline call.
For the in-line sites we replace the CALL with a NOP5.
NOTE: this is 'obviously' limited to functions with a 'void' return type.
NOTE: DEFINE_STATIC_COND_CALL() only requires a typename, as opposed
to a full function.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.042977182@infradead.org
Add the inline static call implementation for x86-64. The generated code
is identical to the out-of-line case, except we move the trampoline into
it's own section.
Objtool uses the trampoline naming convention to detect all the call
sites. It then annotates those call sites in the .static_call_sites
section.
During boot (and module init), the call sites are patched to call
directly into the destination function. The temporary trampoline is
then no longer used.
[peterz: merged trampolines, put trampoline in section]
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.864271425@infradead.org
Add the x86 out-of-line static call implementation. For each key, a
permanent trampoline is created which is the destination for all static
calls for the given key. The trampoline has a direct jump which gets
patched by static_call_update() when the destination function changes.
[peterz: fixed trampoline, rewrote patching code]
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.804315175@infradead.org
