Linus Torvalds f557af081d RISC-V Patches for the 6.11 Merge Window, Part 1
* Support for various new ISA extensions:
     * The Zve32[xf] and Zve64[xfd] sub-extensios of the vector
       extension.
     * Zimop and Zcmop for may-be-operations.
     * The Zca, Zcf, Zcd and Zcb sub-extensions of the C extension.
     * Zawrs,
 * riscv,cpu-intc is now dtschema.
 * A handful of performance improvements and cleanups to text patching.
 * Support for memory hot{,un}plug
 * The highest user-allocatable virtual address is now visible in
   hwprobe.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAmabIGETHHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYiQe8D/9QPCaOnoP5OCZbwjkRBwaVxyknNyD0
 l+YNXk7Jk3B/oaOv3d7Bz+uWt1SG4j4jkfyuGJ81StZykp4/R7T823TZrPhog9VX
 IJm580MtvE49I2i1qJ+ZQti9wpiM+80lFnyMCzY6S7rrM9m62tKgUpARZcWoA55P
 iUo5bku99TYCcU2k1pnPrNSPQvVpECpv7tG0PwKpQd5DiYjbPp+aw5cQWN+izdOB
 6raOZ0buzP7McszvO/gcJs+kuHwrp0JSRvNxc2pwYZ0lx00p3hSV8UdtIMlI9Qm/
 z3gkQGHwc6UVMPHo1x0Gr5ShUTCI/iSwy4/7aY4NNXF6Sj99b8alt9GcbYqNAE7V
 k7sibCR7dhL4ods/GFMmzR7cQYlwlwtO+/ILak7rXhNvA32Xy1WUABguhP9ElTmw
 1ZS2hnRv6wc7MA2V7HBamf5mPXM6HQyC3oKy3njzDSJdiGIG7aa+TOfRAD+L/1Du
 QjIrKp6XcPIsZNjh8H3nMDVJ0VvDNnS4d4LbfNQc23VPzf57kFUqbli1pS0hBjFT
 ELEItH9dgSx+T5Qebdy/QMC3RG8Yc1IUdw6VQ7Jny/uCCEZNq+VZ+bXxspMmswCp
 sUIyDplJTJfRt3G2OxK0b95x6oj8jbaJOQfv6PBF71dDBsChg8eXFVJ2NDrX4Bvr
 h2MPK7vGBtFz8w==
 =+ICi
 -----END PGP SIGNATURE-----

Merge tag 'riscv-for-linus-6.11-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Support for various new ISA extensions:
     * The Zve32[xf] and Zve64[xfd] sub-extensios of the vector
       extension
     * Zimop and Zcmop for may-be-operations
     * The Zca, Zcf, Zcd and Zcb sub-extensions of the C extension
     * Zawrs

 - riscv,cpu-intc is now dtschema

 - A handful of performance improvements and cleanups to text patching

 - Support for memory hot{,un}plug

 - The highest user-allocatable virtual address is now visible in
   hwprobe

* tag 'riscv-for-linus-6.11-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (58 commits)
  riscv: lib: relax assembly constraints in hweight
  riscv: set trap vector earlier
  KVM: riscv: selftests: Add Zawrs extension to get-reg-list test
  KVM: riscv: Support guest wrs.nto
  riscv: hwprobe: export Zawrs ISA extension
  riscv: Add Zawrs support for spinlocks
  dt-bindings: riscv: Add Zawrs ISA extension description
  riscv: Provide a definition for 'pause'
  riscv: hwprobe: export highest virtual userspace address
  riscv: Improve sbi_ecall() code generation by reordering arguments
  riscv: Add tracepoints for SBI calls and returns
  riscv: Optimize crc32 with Zbc extension
  riscv: Enable DAX VMEMMAP optimization
  riscv: mm: Add support for ZONE_DEVICE
  virtio-mem: Enable virtio-mem for RISC-V
  riscv: Enable memory hotplugging for RISC-V
  riscv: mm: Take memory hotplug read-lock during kernel page table dump
  riscv: mm: Add memory hotplugging support
  riscv: mm: Add pfn_to_kaddr() implementation
  riscv: mm: Refactor create_linear_mapping_range() for memory hot add
  ...
2024-07-20 09:11:27 -07:00

298 lines
6.9 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2020 SiFive
*/
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/memory.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/stop_machine.h>
#include <asm/kprobes.h>
#include <asm/cacheflush.h>
#include <asm/fixmap.h>
#include <asm/ftrace.h>
#include <asm/patch.h>
#include <asm/sections.h>
struct patch_insn {
void *addr;
u32 *insns;
size_t len;
atomic_t cpu_count;
};
int riscv_patch_in_stop_machine = false;
#ifdef CONFIG_MMU
static inline bool is_kernel_exittext(uintptr_t addr)
{
return system_state < SYSTEM_RUNNING &&
addr >= (uintptr_t)__exittext_begin &&
addr < (uintptr_t)__exittext_end;
}
/*
* The fix_to_virt(, idx) needs a const value (not a dynamic variable of
* reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses".
* So use '__always_inline' and 'const unsigned int fixmap' here.
*/
static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
{
uintptr_t uintaddr = (uintptr_t) addr;
struct page *page;
if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr))
page = phys_to_page(__pa_symbol(addr));
else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
page = vmalloc_to_page(addr);
else
return addr;
BUG_ON(!page);
return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
offset_in_page(addr));
}
static void patch_unmap(int fixmap)
{
clear_fixmap(fixmap);
}
NOKPROBE_SYMBOL(patch_unmap);
static int __patch_insn_set(void *addr, u8 c, size_t len)
{
bool across_pages = (offset_in_page(addr) + len) > PAGE_SIZE;
void *waddr = addr;
/*
* Only two pages can be mapped at a time for writing.
*/
if (len + offset_in_page(addr) > 2 * PAGE_SIZE)
return -EINVAL;
/*
* Before reaching here, it was expected to lock the text_mutex
* already, so we don't need to give another lock here and could
* ensure that it was safe between each cores.
*/
lockdep_assert_held(&text_mutex);
preempt_disable();
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
waddr = patch_map(addr, FIX_TEXT_POKE0);
memset(waddr, c, len);
/*
* We could have just patched a function that is about to be
* called so make sure we don't execute partially patched
* instructions by flushing the icache as soon as possible.
*/
local_flush_icache_range((unsigned long)waddr,
(unsigned long)waddr + len);
patch_unmap(FIX_TEXT_POKE0);
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
preempt_enable();
return 0;
}
NOKPROBE_SYMBOL(__patch_insn_set);
static int __patch_insn_write(void *addr, const void *insn, size_t len)
{
bool across_pages = (offset_in_page(addr) + len) > PAGE_SIZE;
void *waddr = addr;
int ret;
/*
* Only two pages can be mapped at a time for writing.
*/
if (len + offset_in_page(addr) > 2 * PAGE_SIZE)
return -EINVAL;
/*
* Before reaching here, it was expected to lock the text_mutex
* already, so we don't need to give another lock here and could
* ensure that it was safe between each cores.
*
* We're currently using stop_machine() for ftrace & kprobes, and while
* that ensures text_mutex is held before installing the mappings it
* does not ensure text_mutex is held by the calling thread. That's
* safe but triggers a lockdep failure, so just elide it for that
* specific case.
*/
if (!riscv_patch_in_stop_machine)
lockdep_assert_held(&text_mutex);
preempt_disable();
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
waddr = patch_map(addr, FIX_TEXT_POKE0);
ret = copy_to_kernel_nofault(waddr, insn, len);
/*
* We could have just patched a function that is about to be
* called so make sure we don't execute partially patched
* instructions by flushing the icache as soon as possible.
*/
local_flush_icache_range((unsigned long)waddr,
(unsigned long)waddr + len);
patch_unmap(FIX_TEXT_POKE0);
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
preempt_enable();
return ret;
}
NOKPROBE_SYMBOL(__patch_insn_write);
#else
static int __patch_insn_set(void *addr, u8 c, size_t len)
{
memset(addr, c, len);
return 0;
}
NOKPROBE_SYMBOL(__patch_insn_set);
static int __patch_insn_write(void *addr, const void *insn, size_t len)
{
return copy_to_kernel_nofault(addr, insn, len);
}
NOKPROBE_SYMBOL(__patch_insn_write);
#endif /* CONFIG_MMU */
static int patch_insn_set(void *addr, u8 c, size_t len)
{
size_t size;
int ret;
/*
* __patch_insn_set() can only work on 2 pages at a time so call it in a
* loop with len <= 2 * PAGE_SIZE.
*/
while (len) {
size = min(len, PAGE_SIZE * 2 - offset_in_page(addr));
ret = __patch_insn_set(addr, c, size);
if (ret)
return ret;
addr += size;
len -= size;
}
return 0;
}
NOKPROBE_SYMBOL(patch_insn_set);
int patch_text_set_nosync(void *addr, u8 c, size_t len)
{
int ret;
ret = patch_insn_set(addr, c, len);
return ret;
}
NOKPROBE_SYMBOL(patch_text_set_nosync);
int patch_insn_write(void *addr, const void *insn, size_t len)
{
size_t size;
int ret;
/*
* Copy the instructions to the destination address, two pages at a time
* because __patch_insn_write() can only handle len <= 2 * PAGE_SIZE.
*/
while (len) {
size = min(len, PAGE_SIZE * 2 - offset_in_page(addr));
ret = __patch_insn_write(addr, insn, size);
if (ret)
return ret;
addr += size;
insn += size;
len -= size;
}
return 0;
}
NOKPROBE_SYMBOL(patch_insn_write);
int patch_text_nosync(void *addr, const void *insns, size_t len)
{
int ret;
ret = patch_insn_write(addr, insns, len);
return ret;
}
NOKPROBE_SYMBOL(patch_text_nosync);
static int patch_text_cb(void *data)
{
struct patch_insn *patch = data;
int ret = 0;
if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) {
ret = patch_insn_write(patch->addr, patch->insns, patch->len);
/*
* Make sure the patching store is effective *before* we
* increment the counter which releases all waiting CPUs
* by using the release variant of atomic increment. The
* release pairs with the call to local_flush_icache_all()
* on the waiting CPU.
*/
atomic_inc_return_release(&patch->cpu_count);
} else {
while (atomic_read(&patch->cpu_count) <= num_online_cpus())
cpu_relax();
local_flush_icache_all();
}
return ret;
}
NOKPROBE_SYMBOL(patch_text_cb);
int patch_text(void *addr, u32 *insns, size_t len)
{
int ret;
struct patch_insn patch = {
.addr = addr,
.insns = insns,
.len = len,
.cpu_count = ATOMIC_INIT(0),
};
/*
* kprobes takes text_mutex, before calling patch_text(), but as we call
* calls stop_machine(), the lockdep assertion in patch_insn_write()
* gets confused by the context in which the lock is taken.
* Instead, ensure the lock is held before calling stop_machine(), and
* set riscv_patch_in_stop_machine to skip the check in
* patch_insn_write().
*/
lockdep_assert_held(&text_mutex);
riscv_patch_in_stop_machine = true;
ret = stop_machine_cpuslocked(patch_text_cb, &patch, cpu_online_mask);
riscv_patch_in_stop_machine = false;
return ret;
}
NOKPROBE_SYMBOL(patch_text);