linux/arch/powerpc/mm/pgtable_32.c

409 lines
9.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* This file contains the routines setting up the linux page tables.
* -- paulus
*
* Derived from arch/ppc/mm/init.c:
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
*
* Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
* and Cort Dougan (PReP) (cort@cs.nmt.edu)
* Copyright (C) 1996 Paul Mackerras
*
* Derived from "arch/i386/mm/init.c"
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/memblock.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/fixmap.h>
#include <asm/io.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <mm/mmu_decl.h>
unsigned long ioremap_bot;
EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */
powerpc32: PAGE_EXEC required for inittext PAGE_EXEC is required for inittext, otherwise CONFIG_DEBUG_PAGEALLOC ends up with an Oops [ 0.000000] Inode-cache hash table entries: 8192 (order: 1, 32768 bytes) [ 0.000000] Sorting __ex_table... [ 0.000000] bootmem::free_all_bootmem_core nid=0 start=0 end=2000 [ 0.000000] Unable to handle kernel paging request for instruction fetch [ 0.000000] Faulting instruction address: 0xc045b970 [ 0.000000] Oops: Kernel access of bad area, sig: 11 [#1] [ 0.000000] PREEMPT DEBUG_PAGEALLOC CMPC885 [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 3.18.25-local-dirty #1673 [ 0.000000] task: c04d83d0 ti: c04f8000 task.ti: c04f8000 [ 0.000000] NIP: c045b970 LR: c045b970 CTR: 0000000a [ 0.000000] REGS: c04f9ea0 TRAP: 0400 Not tainted (3.18.25-local-dirty) [ 0.000000] MSR: 08001032 <ME,IR,DR,RI> CR: 39955d35 XER: a000ff40 [ 0.000000] GPR00: c045b970 c04f9f50 c04d83d0 00000000 ffffffff c04dcdf4 00000048 c04f6b10 GPR08: c04f6ab0 00000001 c0563488 c04f6ab0 c04f8000 00000000 00000000 b6db6db7 GPR16: 00003474 00000180 00002000 c7fec000 00000000 000003ff 00000176 c0415014 GPR24: c0471018 c0414ee8 c05304e8 c03aeaac c0510000 c0471018 c0471010 00000000 [ 0.000000] NIP [c045b970] free_all_bootmem+0x164/0x228 [ 0.000000] LR [c045b970] free_all_bootmem+0x164/0x228 [ 0.000000] Call Trace: [ 0.000000] [c04f9f50] [c045b970] free_all_bootmem+0x164/0x228 (unreliable) [ 0.000000] [c04f9fa0] [c0454044] mem_init+0x3c/0xd0 [ 0.000000] [c04f9fb0] [c045080c] start_kernel+0x1f4/0x390 [ 0.000000] [c04f9ff0] [c0002214] start_here+0x38/0x98 [ 0.000000] Instruction dump: [ 0.000000] 2f150000 7f968840 72a90001 3ad60001 56b5f87e 419a0028 419e0024 41a20018 [ 0.000000] 807cc20c 38800000 7c638214 4bffd2f5 <3a940001> 3a100024 4bffffc8 7e368b78 [ 0.000000] ---[ end trace dc8fa200cb88537f ]--- Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Scott Wood <oss@buserror.net>
2016-02-10 15:17:08 +08:00
extern char etext[], _stext[], _sinittext[], _einittext[];
void __iomem *
ioremap(phys_addr_t addr, unsigned long size)
{
pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap);
void __iomem *
ioremap_wc(phys_addr_t addr, unsigned long size)
{
pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_wc);
void __iomem *
ioremap_wt(phys_addr_t addr, unsigned long size)
{
pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL);
return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_wt);
void __iomem *
ioremap_coherent(phys_addr_t addr, unsigned long size)
{
pgprot_t prot = pgprot_cached(PAGE_KERNEL);
return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_coherent);
void __iomem *
ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
{
pte_t pte = __pte(flags);
/* writeable implies dirty for kernel addresses */
if (pte_write(pte))
pte = pte_mkdirty(pte);
/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
pte = pte_exprotect(pte);
pte = pte_mkprivileged(pte);
return __ioremap_caller(addr, size, pte_pgprot(pte), __builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_prot);
void __iomem *
__ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
{
return __ioremap_caller(addr, size, __pgprot(flags), __builtin_return_address(0));
}
void __iomem *
__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
{
unsigned long v, i;
phys_addr_t p;
int err;
/*
* Choose an address to map it to.
* Once the vmalloc system is running, we use it.
* Before then, we use space going down from IOREMAP_TOP
* (ioremap_bot records where we're up to).
*/
p = addr & PAGE_MASK;
size = PAGE_ALIGN(addr + size) - p;
/*
* If the address lies within the first 16 MB, assume it's in ISA
* memory space
*/
if (p < 16*1024*1024)
p += _ISA_MEM_BASE;
#ifndef CONFIG_CRASH_DUMP
/*
* Don't allow anybody to remap normal RAM that we're using.
* mem_init() sets high_memory so only do the check after that.
*/
powerpc: implement CONFIG_DEBUG_VIRTUAL This patch implements CONFIG_DEBUG_VIRTUAL to warn about incorrect use of virt_to_phys() and page_to_phys() Below is the result of test_debug_virtual: [ 1.438746] WARNING: CPU: 0 PID: 1 at ./arch/powerpc/include/asm/io.h:808 test_debug_virtual_init+0x3c/0xd4 [ 1.448156] CPU: 0 PID: 1 Comm: swapper Not tainted 4.20.0-rc5-00560-g6bfb52e23a00-dirty #532 [ 1.457259] NIP: c066c550 LR: c0650ccc CTR: c066c514 [ 1.462257] REGS: c900bdb0 TRAP: 0700 Not tainted (4.20.0-rc5-00560-g6bfb52e23a00-dirty) [ 1.471184] MSR: 00029032 <EE,ME,IR,DR,RI> CR: 48000422 XER: 20000000 [ 1.477811] [ 1.477811] GPR00: c0650ccc c900be60 c60d0000 00000000 006000c0 c9000000 00009032 c7fa0020 [ 1.477811] GPR08: 00002400 00000001 09000000 00000000 c07b5d04 00000000 c00037d8 00000000 [ 1.477811] GPR16: 00000000 00000000 00000000 00000000 c0760000 c0740000 00000092 c0685bb0 [ 1.477811] GPR24: c065042c c068a734 c0685b8c 00000006 00000000 c0760000 c075c3c0 ffffffff [ 1.512711] NIP [c066c550] test_debug_virtual_init+0x3c/0xd4 [ 1.518315] LR [c0650ccc] do_one_initcall+0x8c/0x1cc [ 1.523163] Call Trace: [ 1.525595] [c900be60] [c0567340] 0xc0567340 (unreliable) [ 1.530954] [c900be90] [c0650ccc] do_one_initcall+0x8c/0x1cc [ 1.536551] [c900bef0] [c0651000] kernel_init_freeable+0x1f4/0x2cc [ 1.542658] [c900bf30] [c00037ec] kernel_init+0x14/0x110 [ 1.547913] [c900bf40] [c000e1d0] ret_from_kernel_thread+0x14/0x1c [ 1.553971] Instruction dump: [ 1.556909] 3ca50100 bfa10024 54a5000e 3fa0c076 7c0802a6 3d454000 813dc204 554893be [ 1.564566] 7d294010 7d294910 90010034 39290001 <0f090000> 7c3e0b78 955e0008 3fe0c062 [ 1.572425] ---[ end trace 6f6984225b280ad6 ]--- [ 1.577467] PA: 0x09000000 for VA: 0xc9000000 [ 1.581799] PA: 0x061e8f50 for VA: 0xc61e8f50 Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-12-19 15:09:39 +08:00
if (slab_is_available() && p <= virt_to_phys(high_memory - 1) &&
page_is_ram(__phys_to_pfn(p))) {
printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n",
(unsigned long long)p, __builtin_return_address(0));
return NULL;
}
#endif
if (size == 0)
return NULL;
/*
* Is it already mapped? Perhaps overlapped by a previous
* mapping.
*/
v = p_block_mapped(p);
if (v)
goto out;
if (slab_is_available()) {
struct vm_struct *area;
area = get_vm_area_caller(size, VM_IOREMAP, caller);
if (area == 0)
return NULL;
area->phys_addr = p;
v = (unsigned long) area->addr;
} else {
v = (ioremap_bot -= size);
}
/*
* Should check if it is a candidate for a BAT mapping
*/
err = 0;
for (i = 0; i < size && err == 0; i += PAGE_SIZE)
err = map_kernel_page(v + i, p + i, prot);
if (err) {
if (slab_is_available())
vunmap((void *)v);
return NULL;
}
out:
return (void __iomem *) (v + ((unsigned long)addr & ~PAGE_MASK));
}
EXPORT_SYMBOL(__ioremap);
void iounmap(volatile void __iomem *addr)
{
/*
* If mapped by BATs then there is nothing to do.
* Calling vfree() generates a benign warning.
*/
if (v_block_mapped((unsigned long)addr))
return;
if (addr > high_memory && (unsigned long) addr < ioremap_bot)
vunmap((void *) (PAGE_MASK & (unsigned long)addr));
}
EXPORT_SYMBOL(iounmap);
static void __init *early_alloc_pgtable(unsigned long size)
{
void *ptr = memblock_alloc(size, size);
if (!ptr)
panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
__func__, size, size);
return ptr;
}
static pte_t __init *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va)
{
if (pmd_none(*pmdp)) {
pte_t *ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
pmd_populate_kernel(&init_mm, pmdp, ptep);
}
return pte_offset_kernel(pmdp, va);
}
int __ref map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot)
{
pmd_t *pd;
pte_t *pg;
int err = -ENOMEM;
/* Use upper 10 bits of VA to index the first level map */
pd = pmd_offset(pud_offset(pgd_offset_k(va), va), va);
/* Use middle 10 bits of VA to index the second-level map */
if (likely(slab_is_available()))
pg = pte_alloc_kernel(pd, va);
else
pg = early_pte_alloc_kernel(pd, va);
if (pg != 0) {
err = 0;
/* The PTE should never be already set nor present in the
* hash table
*/
BUG_ON((pte_present(*pg) | pte_hashpte(*pg)) && pgprot_val(prot));
set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT, prot));
}
smp_wmb();
return err;
}
/*
* Map in a chunk of physical memory starting at start.
*/
static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
{
unsigned long v, s;
phys_addr_t p;
int ktext;
s = offset;
v = PAGE_OFFSET + s;
p = memstart_addr + s;
for (; s < top; s += PAGE_SIZE) {
powerpc32: PAGE_EXEC required for inittext PAGE_EXEC is required for inittext, otherwise CONFIG_DEBUG_PAGEALLOC ends up with an Oops [ 0.000000] Inode-cache hash table entries: 8192 (order: 1, 32768 bytes) [ 0.000000] Sorting __ex_table... [ 0.000000] bootmem::free_all_bootmem_core nid=0 start=0 end=2000 [ 0.000000] Unable to handle kernel paging request for instruction fetch [ 0.000000] Faulting instruction address: 0xc045b970 [ 0.000000] Oops: Kernel access of bad area, sig: 11 [#1] [ 0.000000] PREEMPT DEBUG_PAGEALLOC CMPC885 [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 3.18.25-local-dirty #1673 [ 0.000000] task: c04d83d0 ti: c04f8000 task.ti: c04f8000 [ 0.000000] NIP: c045b970 LR: c045b970 CTR: 0000000a [ 0.000000] REGS: c04f9ea0 TRAP: 0400 Not tainted (3.18.25-local-dirty) [ 0.000000] MSR: 08001032 <ME,IR,DR,RI> CR: 39955d35 XER: a000ff40 [ 0.000000] GPR00: c045b970 c04f9f50 c04d83d0 00000000 ffffffff c04dcdf4 00000048 c04f6b10 GPR08: c04f6ab0 00000001 c0563488 c04f6ab0 c04f8000 00000000 00000000 b6db6db7 GPR16: 00003474 00000180 00002000 c7fec000 00000000 000003ff 00000176 c0415014 GPR24: c0471018 c0414ee8 c05304e8 c03aeaac c0510000 c0471018 c0471010 00000000 [ 0.000000] NIP [c045b970] free_all_bootmem+0x164/0x228 [ 0.000000] LR [c045b970] free_all_bootmem+0x164/0x228 [ 0.000000] Call Trace: [ 0.000000] [c04f9f50] [c045b970] free_all_bootmem+0x164/0x228 (unreliable) [ 0.000000] [c04f9fa0] [c0454044] mem_init+0x3c/0xd0 [ 0.000000] [c04f9fb0] [c045080c] start_kernel+0x1f4/0x390 [ 0.000000] [c04f9ff0] [c0002214] start_here+0x38/0x98 [ 0.000000] Instruction dump: [ 0.000000] 2f150000 7f968840 72a90001 3ad60001 56b5f87e 419a0028 419e0024 41a20018 [ 0.000000] 807cc20c 38800000 7c638214 4bffd2f5 <3a940001> 3a100024 4bffffc8 7e368b78 [ 0.000000] ---[ end trace dc8fa200cb88537f ]--- Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Scott Wood <oss@buserror.net>
2016-02-10 15:17:08 +08:00
ktext = ((char *)v >= _stext && (char *)v < etext) ||
((char *)v >= _sinittext && (char *)v < _einittext);
map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL);
#ifdef CONFIG_PPC_BOOK3S_32
if (ktext)
hash_preload(&init_mm, v, false, 0x300);
#endif
v += PAGE_SIZE;
p += PAGE_SIZE;
}
}
void __init mapin_ram(void)
{
struct memblock_region *reg;
for_each_memblock(memory, reg) {
phys_addr_t base = reg->base;
phys_addr_t top = min(base + reg->size, total_lowmem);
if (base >= top)
continue;
base = mmu_mapin_ram(base, top);
if (IS_ENABLED(CONFIG_BDI_SWITCH))
__mapin_ram_chunk(reg->base, top);
else
__mapin_ram_chunk(base, top);
}
}
/* Scan the real Linux page tables and return a PTE pointer for
* a virtual address in a context.
* Returns true (1) if PTE was found, zero otherwise. The pointer to
* the PTE pointer is unmodified if PTE is not found.
*/
static int
get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, pmd_t **pmdp)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
int retval = 0;
pgd = pgd_offset(mm, addr & PAGE_MASK);
if (pgd) {
pud = pud_offset(pgd, addr & PAGE_MASK);
if (pud && pud_present(*pud)) {
pmd = pmd_offset(pud, addr & PAGE_MASK);
if (pmd_present(*pmd)) {
pte = pte_offset_map(pmd, addr & PAGE_MASK);
if (pte) {
retval = 1;
*ptep = pte;
if (pmdp)
*pmdp = pmd;
/* XXX caller needs to do pte_unmap, yuck */
}
}
}
}
return(retval);
}
static int __change_page_attr_noflush(struct page *page, pgprot_t prot)
{
pte_t *kpte;
pmd_t *kpmd;
unsigned long address;
BUG_ON(PageHighMem(page));
address = (unsigned long)page_address(page);
if (v_block_mapped(address))
return 0;
if (!get_pteptr(&init_mm, address, &kpte, &kpmd))
return -EINVAL;
__set_pte_at(&init_mm, address, kpte, mk_pte(page, prot), 0);
pte_unmap(kpte);
return 0;
}
/*
* Change the page attributes of an page in the linear mapping.
*
* THIS DOES NOTHING WITH BAT MAPPINGS, DEBUG USE ONLY
*/
static int change_page_attr(struct page *page, int numpages, pgprot_t prot)
{
int i, err = 0;
unsigned long flags;
struct page *start = page;
local_irq_save(flags);
for (i = 0; i < numpages; i++, page++) {
err = __change_page_attr_noflush(page, prot);
if (err)
break;
}
wmb();
powerpc/mm: Call flush_tlb_kernel_range with interrupts enabled flush_tlb_kernel_range() may call smp_call_function_many() which expects interrupts to be enabled. This results in a traceback. WARNING: CPU: 0 PID: 1 at kernel/smp.c:416 smp_call_function_many+0xcc/0x2fc CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.14.0-rc1-00009-g0666f56 #1 task: cf830000 task.stack: cf82e000 NIP: c00a93c8 LR: c00a9634 CTR: 00000001 REGS: cf82fde0 TRAP: 0700 Not tainted (4.14.0-rc1-00009-g0666f56) MSR: 00021000 <CE,ME> CR: 24000082 XER: 00000000 GPR00: c00a9634 cf82fe90 cf830000 c050ad3c c0015a54 00000000 00000001 00000001 GPR08: 00000001 00000000 00000000 cf82e000 24000084 00000000 c0003150 00000000 GPR16: 00000000 00000000 00000000 00000000 00000000 00000001 00000000 c0510000 GPR24: 00000000 c0015a54 00000000 c050ad3c c051823c c050ad3c 00000025 00000000 NIP [c00a93c8] smp_call_function_many+0xcc/0x2fc LR [c00a9634] smp_call_function+0x3c/0x50 Call Trace: [cf82fe90] [00000010] 0x10 (unreliable) [cf82fed0] [c00a9634] smp_call_function+0x3c/0x50 [cf82fee0] [c0015d2c] flush_tlb_kernel_range+0x20/0x38 [cf82fef0] [c001524c] mark_initmem_nx+0x154/0x16c [cf82ff20] [c001484c] free_initmem+0x20/0x4c [cf82ff30] [c000316c] kernel_init+0x1c/0x108 [cf82ff40] [c000f3a8] ret_from_kernel_thread+0x5c/0x64 Instruction dump: 7c0803a6 7d808120 38210040 4e800020 3d20c052 812981a0 2f890000 40beffac 3d20c051 8929ac64 2f890000 40beff9c <0fe00000> 4bffff94 7fc3f378 7f64db78 Fixes: 3184cc4b6f6a ("powerpc/mm: Fix kernel RAM protection after freeing ...") Fixes: e611939fc8ec ("powerpc/mm: Ensure change_page_attr() doesn't ...") Cc: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-25 01:30:43 +08:00
local_irq_restore(flags);
flush_tlb_kernel_range((unsigned long)page_address(start),
(unsigned long)page_address(page));
return err;
}
void mark_initmem_nx(void)
{
struct page *page = virt_to_page(_sinittext);
unsigned long numpages = PFN_UP((unsigned long)_einittext) -
PFN_DOWN((unsigned long)_sinittext);
if (v_block_mapped((unsigned long)_stext + 1))
powerpc/mm/32s: Use BATs for STRICT_KERNEL_RWX Today, STRICT_KERNEL_RWX is based on the use of regular pages to map kernel pages. On Book3s 32, it has three consequences: - Using pages instead of BAT for mapping kernel linear memory severely impacts performance. - Exec protection is not effective because no-execute cannot be set at page level (except on 603 which doesn't have hash tables) - Write protection is not effective because PP bits do not provide RO mode for kernel-only pages (except on 603 which handles it in software via PAGE_DIRTY) On the 603+, we have: - Independent IBAT and DBAT allowing limitation of exec parts. - NX bit can be set in segment registers to forbit execution on memory mapped by pages. - RO mode on DBATs even for kernel-only blocks. On the 601, there is nothing much we can do other than warn the user about it, because: - BATs are common to instructions and data. - BAT do not provide RO mode for kernel-only blocks. - segment registers don't have the NX bit. In order to use IBAT for exec protection, this patch: - Aligns _etext to BAT block sizes (128kb) - Set NX bit in kernel segment register (Except on vmalloc area when CONFIG_MODULES is selected) - Maps kernel text with IBATs. In order to use DBAT for exec protection, this patch: - Aligns RW DATA to BAT block sizes (4M) - Maps kernel RO area with write prohibited DBATs - Maps remaining memory with remaining DBATs Here is what we get with this patch on a 832x when activating STRICT_KERNEL_RWX: Symbols: c0000000 T _stext c0680000 R __start_rodata c0680000 R _etext c0800000 T __init_begin c0800000 T _sinittext ~# cat /sys/kernel/debug/block_address_translation ---[ Instruction Block Address Translation ]--- 0: 0xc0000000-0xc03fffff 0x00000000 Kernel EXEC coherent 1: 0xc0400000-0xc05fffff 0x00400000 Kernel EXEC coherent 2: 0xc0600000-0xc067ffff 0x00600000 Kernel EXEC coherent 3: - 4: - 5: - 6: - 7: - ---[ Data Block Address Translation ]--- 0: 0xc0000000-0xc07fffff 0x00000000 Kernel RO coherent 1: 0xc0800000-0xc0ffffff 0x00800000 Kernel RW coherent 2: 0xc1000000-0xc1ffffff 0x01000000 Kernel RW coherent 3: 0xc2000000-0xc3ffffff 0x02000000 Kernel RW coherent 4: 0xc4000000-0xc7ffffff 0x04000000 Kernel RW coherent 5: 0xc8000000-0xcfffffff 0x08000000 Kernel RW coherent 6: 0xd0000000-0xdfffffff 0x10000000 Kernel RW coherent 7: - ~# cat /sys/kernel/debug/segment_registers ---[ User Segments ]--- 0x00000000-0x0fffffff Kern key 1 User key 1 VSID 0xa085d0 0x10000000-0x1fffffff Kern key 1 User key 1 VSID 0xa086e1 0x20000000-0x2fffffff Kern key 1 User key 1 VSID 0xa087f2 0x30000000-0x3fffffff Kern key 1 User key 1 VSID 0xa08903 0x40000000-0x4fffffff Kern key 1 User key 1 VSID 0xa08a14 0x50000000-0x5fffffff Kern key 1 User key 1 VSID 0xa08b25 0x60000000-0x6fffffff Kern key 1 User key 1 VSID 0xa08c36 0x70000000-0x7fffffff Kern key 1 User key 1 VSID 0xa08d47 0x80000000-0x8fffffff Kern key 1 User key 1 VSID 0xa08e58 0x90000000-0x9fffffff Kern key 1 User key 1 VSID 0xa08f69 0xa0000000-0xafffffff Kern key 1 User key 1 VSID 0xa0907a 0xb0000000-0xbfffffff Kern key 1 User key 1 VSID 0xa0918b ---[ Kernel Segments ]--- 0xc0000000-0xcfffffff Kern key 0 User key 1 No Exec VSID 0x000ccc 0xd0000000-0xdfffffff Kern key 0 User key 1 No Exec VSID 0x000ddd 0xe0000000-0xefffffff Kern key 0 User key 1 No Exec VSID 0x000eee 0xf0000000-0xffffffff Kern key 0 User key 1 No Exec VSID 0x000fff Aligning _etext to 128kb allows to map up to 32Mb text with 8 IBATs: 16Mb + 8Mb + 4Mb + 2Mb + 1Mb + 512kb + 256kb + 128kb (+ 128kb) = 32Mb (A 9th IBAT is unneeded as 32Mb would need only a single 32Mb block) Aligning data to 4M allows to map up to 512Mb data with 8 DBATs: 16Mb + 8Mb + 4Mb + 4Mb + 32Mb + 64Mb + 128Mb + 256Mb = 512Mb Because some processors only have 4 BATs and because some targets need DBATs for mapping other areas, the following patch will allow to modify _etext and data alignment. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-02-22 03:08:49 +08:00
mmu_mark_initmem_nx();
else
change_page_attr(page, numpages, PAGE_KERNEL);
}
#ifdef CONFIG_STRICT_KERNEL_RWX
void mark_rodata_ro(void)
{
struct page *page;
unsigned long numpages;
powerpc/mm/32s: Use BATs for STRICT_KERNEL_RWX Today, STRICT_KERNEL_RWX is based on the use of regular pages to map kernel pages. On Book3s 32, it has three consequences: - Using pages instead of BAT for mapping kernel linear memory severely impacts performance. - Exec protection is not effective because no-execute cannot be set at page level (except on 603 which doesn't have hash tables) - Write protection is not effective because PP bits do not provide RO mode for kernel-only pages (except on 603 which handles it in software via PAGE_DIRTY) On the 603+, we have: - Independent IBAT and DBAT allowing limitation of exec parts. - NX bit can be set in segment registers to forbit execution on memory mapped by pages. - RO mode on DBATs even for kernel-only blocks. On the 601, there is nothing much we can do other than warn the user about it, because: - BATs are common to instructions and data. - BAT do not provide RO mode for kernel-only blocks. - segment registers don't have the NX bit. In order to use IBAT for exec protection, this patch: - Aligns _etext to BAT block sizes (128kb) - Set NX bit in kernel segment register (Except on vmalloc area when CONFIG_MODULES is selected) - Maps kernel text with IBATs. In order to use DBAT for exec protection, this patch: - Aligns RW DATA to BAT block sizes (4M) - Maps kernel RO area with write prohibited DBATs - Maps remaining memory with remaining DBATs Here is what we get with this patch on a 832x when activating STRICT_KERNEL_RWX: Symbols: c0000000 T _stext c0680000 R __start_rodata c0680000 R _etext c0800000 T __init_begin c0800000 T _sinittext ~# cat /sys/kernel/debug/block_address_translation ---[ Instruction Block Address Translation ]--- 0: 0xc0000000-0xc03fffff 0x00000000 Kernel EXEC coherent 1: 0xc0400000-0xc05fffff 0x00400000 Kernel EXEC coherent 2: 0xc0600000-0xc067ffff 0x00600000 Kernel EXEC coherent 3: - 4: - 5: - 6: - 7: - ---[ Data Block Address Translation ]--- 0: 0xc0000000-0xc07fffff 0x00000000 Kernel RO coherent 1: 0xc0800000-0xc0ffffff 0x00800000 Kernel RW coherent 2: 0xc1000000-0xc1ffffff 0x01000000 Kernel RW coherent 3: 0xc2000000-0xc3ffffff 0x02000000 Kernel RW coherent 4: 0xc4000000-0xc7ffffff 0x04000000 Kernel RW coherent 5: 0xc8000000-0xcfffffff 0x08000000 Kernel RW coherent 6: 0xd0000000-0xdfffffff 0x10000000 Kernel RW coherent 7: - ~# cat /sys/kernel/debug/segment_registers ---[ User Segments ]--- 0x00000000-0x0fffffff Kern key 1 User key 1 VSID 0xa085d0 0x10000000-0x1fffffff Kern key 1 User key 1 VSID 0xa086e1 0x20000000-0x2fffffff Kern key 1 User key 1 VSID 0xa087f2 0x30000000-0x3fffffff Kern key 1 User key 1 VSID 0xa08903 0x40000000-0x4fffffff Kern key 1 User key 1 VSID 0xa08a14 0x50000000-0x5fffffff Kern key 1 User key 1 VSID 0xa08b25 0x60000000-0x6fffffff Kern key 1 User key 1 VSID 0xa08c36 0x70000000-0x7fffffff Kern key 1 User key 1 VSID 0xa08d47 0x80000000-0x8fffffff Kern key 1 User key 1 VSID 0xa08e58 0x90000000-0x9fffffff Kern key 1 User key 1 VSID 0xa08f69 0xa0000000-0xafffffff Kern key 1 User key 1 VSID 0xa0907a 0xb0000000-0xbfffffff Kern key 1 User key 1 VSID 0xa0918b ---[ Kernel Segments ]--- 0xc0000000-0xcfffffff Kern key 0 User key 1 No Exec VSID 0x000ccc 0xd0000000-0xdfffffff Kern key 0 User key 1 No Exec VSID 0x000ddd 0xe0000000-0xefffffff Kern key 0 User key 1 No Exec VSID 0x000eee 0xf0000000-0xffffffff Kern key 0 User key 1 No Exec VSID 0x000fff Aligning _etext to 128kb allows to map up to 32Mb text with 8 IBATs: 16Mb + 8Mb + 4Mb + 2Mb + 1Mb + 512kb + 256kb + 128kb (+ 128kb) = 32Mb (A 9th IBAT is unneeded as 32Mb would need only a single 32Mb block) Aligning data to 4M allows to map up to 512Mb data with 8 DBATs: 16Mb + 8Mb + 4Mb + 4Mb + 32Mb + 64Mb + 128Mb + 256Mb = 512Mb Because some processors only have 4 BATs and because some targets need DBATs for mapping other areas, the following patch will allow to modify _etext and data alignment. Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2019-02-22 03:08:49 +08:00
if (v_block_mapped((unsigned long)_sinittext)) {
mmu_mark_rodata_ro();
return;
}
page = virt_to_page(_stext);
numpages = PFN_UP((unsigned long)_etext) -
PFN_DOWN((unsigned long)_stext);
change_page_attr(page, numpages, PAGE_KERNEL_ROX);
/*
* mark .rodata as read only. Use __init_begin rather than __end_rodata
* to cover NOTES and EXCEPTION_TABLE.
*/
page = virt_to_page(__start_rodata);
numpages = PFN_UP((unsigned long)__init_begin) -
PFN_DOWN((unsigned long)__start_rodata);
change_page_attr(page, numpages, PAGE_KERNEL_RO);
// mark_initmem_nx() should have already run by now
ptdump_check_wx();
}
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
void __kernel_map_pages(struct page *page, int numpages, int enable)
{
if (PageHighMem(page))
return;
change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0));
}
#endif /* CONFIG_DEBUG_PAGEALLOC */