summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorMichael Ellerman <mpe@ellerman.id.au>2019-11-14 09:19:20 +0100
committerMichael Ellerman <mpe@ellerman.id.au>2019-11-14 09:23:33 +0100
commit3df191118b4ca20f58c7a84e59330c6b9d99454b (patch)
treedc99c81363f288f00d30fd4f63489dc28df7fef6
parentpowerpc/fadump: when fadump is supported register the fadump sysfs files. (diff)
parentpowerpc/fsl_booke/32: Document KASLR implementation (diff)
downloadlinux-3df191118b4ca20f58c7a84e59330c6b9d99454b.tar.xz
linux-3df191118b4ca20f58c7a84e59330c6b9d99454b.zip
Merge branch 'topic/kaslr-book3e32' into next
This is a slight rebase of Scott's next branch, which contained the KASLR support for book3e 32-bit, to squash in a couple of small fixes. See the original pull request: https://lore.kernel.org/r/20191022232155.GA26174@home.buserror.net
-rw-r--r--Documentation/powerpc/index.rst1
-rw-r--r--Documentation/powerpc/kaslr-booke32.rst42
-rw-r--r--arch/powerpc/Kconfig11
-rw-r--r--arch/powerpc/include/asm/nohash/mmu-book3e.h11
-rw-r--r--arch/powerpc/include/asm/page.h7
-rw-r--r--arch/powerpc/kernel/early_32.c9
-rw-r--r--arch/powerpc/kernel/exceptions-64e.S12
-rw-r--r--arch/powerpc/kernel/fsl_booke_entry_mapping.S25
-rw-r--r--arch/powerpc/kernel/head_fsl_booke.S61
-rw-r--r--arch/powerpc/kernel/machine_kexec.c1
-rw-r--r--arch/powerpc/kernel/misc_64.S7
-rw-r--r--arch/powerpc/kernel/setup-common.c20
-rw-r--r--arch/powerpc/mm/init-common.c7
-rw-r--r--arch/powerpc/mm/init_32.c5
-rw-r--r--arch/powerpc/mm/init_64.c5
-rw-r--r--arch/powerpc/mm/mmu_decl.h11
-rw-r--r--arch/powerpc/mm/nohash/Makefile1
-rw-r--r--arch/powerpc/mm/nohash/fsl_booke.c8
-rw-r--r--arch/powerpc/mm/nohash/kaslr_booke.c401
19 files changed, 591 insertions, 54 deletions
diff --git a/Documentation/powerpc/index.rst b/Documentation/powerpc/index.rst
index db7b6a880f52..ba5edb3211c0 100644
--- a/Documentation/powerpc/index.rst
+++ b/Documentation/powerpc/index.rst
@@ -19,6 +19,7 @@ powerpc
firmware-assisted-dump
hvcs
isa-versions
+ kaslr-booke32
mpc52xx
pci_iov_resource_on_powernv
pmu-ebb
diff --git a/Documentation/powerpc/kaslr-booke32.rst b/Documentation/powerpc/kaslr-booke32.rst
new file mode 100644
index 000000000000..8b259fdfdf03
--- /dev/null
+++ b/Documentation/powerpc/kaslr-booke32.rst
@@ -0,0 +1,42 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+KASLR for Freescale BookE32
+===========================
+
+The word KASLR stands for Kernel Address Space Layout Randomization.
+
+This document tries to explain the implementation of the KASLR for
+Freescale BookE32. KASLR is a security feature that deters exploit
+attempts relying on knowledge of the location of kernel internals.
+
+Since CONFIG_RELOCATABLE has already supported, what we need to do is
+map or copy kernel to a proper place and relocate. Freescale Book-E
+parts expect lowmem to be mapped by fixed TLB entries(TLB1). The TLB1
+entries are not suitable to map the kernel directly in a randomized
+region, so we chose to copy the kernel to a proper place and restart to
+relocate.
+
+Entropy is derived from the banner and timer base, which will change every
+build and boot. This not so much safe so additionally the bootloader may
+pass entropy via the /chosen/kaslr-seed node in device tree.
+
+We will use the first 512M of the low memory to randomize the kernel
+image. The memory will be split in 64M zones. We will use the lower 8
+bit of the entropy to decide the index of the 64M zone. Then we chose a
+16K aligned offset inside the 64M zone to put the kernel in::
+
+ KERNELBASE
+
+ |--> 64M <--|
+ | |
+ +---------------+ +----------------+---------------+
+ | |....| |kernel| | |
+ +---------------+ +----------------+---------------+
+ | |
+ |-----> offset <-----|
+
+ kernstart_virt_addr
+
+To enable KASLR, set CONFIG_RANDOMIZE_BASE = y. If KASLR is enable and you
+want to disable it at runtime, add "nokaslr" to the kernel cmdline.
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b0bdfe31d12e..09dddb849671 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -551,6 +551,17 @@ config RELOCATABLE
setting can still be useful to bootwrappers that need to know the
load address of the kernel (eg. u-boot/mkimage).
+config RANDOMIZE_BASE
+ bool "Randomize the address of the kernel image"
+ depends on (FSL_BOOKE && FLATMEM && PPC32)
+ depends on RELOCATABLE
+ help
+ Randomizes the virtual address at which the kernel image is
+ loaded, as a security feature that deters exploit attempts
+ relying on knowledge of the location of kernel internals.
+
+ If unsure, say Y.
+
config RELOCATABLE_TEST
bool "Test relocatable kernel"
depends on (PPC64 && RELOCATABLE)
diff --git a/arch/powerpc/include/asm/nohash/mmu-book3e.h b/arch/powerpc/include/asm/nohash/mmu-book3e.h
index 4c9777d256fb..b41004664312 100644
--- a/arch/powerpc/include/asm/nohash/mmu-book3e.h
+++ b/arch/powerpc/include/asm/nohash/mmu-book3e.h
@@ -75,7 +75,6 @@
#define MAS2_E 0x00000001
#define MAS2_WIMGE_MASK 0x0000001f
#define MAS2_EPN_MASK(size) (~0 << (size + 10))
-#define MAS2_VAL(addr, size, flags) ((addr) & MAS2_EPN_MASK(size) | (flags))
#define MAS3_RPN 0xFFFFF000
#define MAS3_U0 0x00000200
@@ -221,6 +220,16 @@
#define TLBILX_T_CLASS2 6
#define TLBILX_T_CLASS3 7
+/*
+ * The mapping only needs to be cache-coherent on SMP, except on
+ * Freescale e500mc derivatives where it's also needed for coherent DMA.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
+#define MAS2_M_IF_NEEDED MAS2_M
+#else
+#define MAS2_M_IF_NEEDED 0
+#endif
+
#ifndef __ASSEMBLY__
#include <asm/bug.h>
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index c8bb14ff4713..f2f3ed5a8969 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -325,6 +325,13 @@ void arch_free_page(struct page *page, int order);
struct vm_area_struct;
+extern unsigned long kernstart_virt_addr;
+
+static inline unsigned long kaslr_offset(void)
+{
+ return kernstart_virt_addr - KERNELBASE;
+}
+
#include <asm-generic/memory_model.h>
#endif /* __ASSEMBLY__ */
#include <asm/slice.h>
diff --git a/arch/powerpc/kernel/early_32.c b/arch/powerpc/kernel/early_32.c
index 3482118ffe76..ef2ad4945904 100644
--- a/arch/powerpc/kernel/early_32.c
+++ b/arch/powerpc/kernel/early_32.c
@@ -19,10 +19,13 @@
*/
notrace unsigned long __init early_init(unsigned long dt_ptr)
{
- unsigned long offset = reloc_offset();
+ unsigned long kva, offset = reloc_offset();
+
+ kva = *PTRRELOC(&kernstart_virt_addr);
/* First zero the BSS */
- memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start);
+ if (kva == KERNELBASE)
+ memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start);
/*
* Identify the CPU type and fix up code sections
@@ -32,5 +35,5 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
apply_feature_fixups();
- return KERNELBASE + offset;
+ return kva + offset;
}
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 829950b96d29..e4076e3c072d 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1346,16 +1346,6 @@ skpinv: addi r6,r6,1 /* Increment */
sync
isync
-/*
- * The mapping only needs to be cache-coherent on SMP, except on
- * Freescale e500mc derivatives where it's also needed for coherent DMA.
- */
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
-#define M_IF_NEEDED MAS2_M
-#else
-#define M_IF_NEEDED 0
-#endif
-
/* 6. Setup KERNELBASE mapping in TLB[0]
*
* r3 = MAS0 w/TLBSEL & ESEL for the entry we started in
@@ -1368,7 +1358,7 @@ skpinv: addi r6,r6,1 /* Increment */
ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
mtspr SPRN_MAS1,r6
- LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | M_IF_NEEDED)
+ LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | MAS2_M_IF_NEEDED)
mtspr SPRN_MAS2,r6
rlwinm r5,r5,0,0,25
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index ea065282b303..8bccce6544b5 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -153,35 +153,24 @@ skpinv: addi r6,r6,1 /* Increment */
tlbivax 0,r9
TLBSYNC
-/*
- * The mapping only needs to be cache-coherent on SMP, except on
- * Freescale e500mc derivatives where it's also needed for coherent DMA.
- */
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
-#define M_IF_NEEDED MAS2_M
-#else
-#define M_IF_NEEDED 0
-#endif
-
#if defined(ENTRY_MAPPING_BOOT_SETUP)
-/* 6. Setup KERNELBASE mapping in TLB1[0] */
+/* 6. Setup kernstart_virt_addr mapping in TLB1[0] */
lis r6,0x1000 /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
mtspr SPRN_MAS0,r6
lis r6,(MAS1_VALID|MAS1_IPROT)@h
ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
mtspr SPRN_MAS1,r6
- lis r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@h
- ori r6,r6,MAS2_VAL(PAGE_OFFSET, BOOK3E_PAGESZ_64M, M_IF_NEEDED)@l
+ lis r6,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@h
+ ori r6,r6,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@l
+ and r6,r6,r20
+ ori r6,r6,MAS2_M_IF_NEEDED@l
mtspr SPRN_MAS2,r6
mtspr SPRN_MAS3,r8
tlbwe
-/* 7. Jump to KERNELBASE mapping */
- lis r6,(KERNELBASE & ~0xfff)@h
- ori r6,r6,(KERNELBASE & ~0xfff)@l
- rlwinm r7,r25,0,0x03ffffff
- add r6,r7,r6
+/* 7. Jump to kernstart_virt_addr mapping */
+ mr r6,r20
#elif defined(ENTRY_MAPPING_KEXEC_SETUP)
/*
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index adf0505dbe02..838d9d4650c7 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -155,6 +155,8 @@ _ENTRY(_start);
*/
_ENTRY(__early_start)
+ LOAD_REG_ADDR_PIC(r20, kernstart_virt_addr)
+ lwz r20,0(r20)
#define ENTRY_MAPPING_BOOT_SETUP
#include "fsl_booke_entry_mapping.S"
@@ -277,8 +279,8 @@ set_ivor:
ori r6, r6, swapper_pg_dir@l
lis r5, abatron_pteptrs@h
ori r5, r5, abatron_pteptrs@l
- lis r4, KERNELBASE@h
- ori r4, r4, KERNELBASE@l
+ lis r3, kernstart_virt_addr@ha
+ lwz r4, kernstart_virt_addr@l(r3)
stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */
stw r6, 0(r5)
@@ -1067,7 +1069,12 @@ __secondary_start:
mr r5,r25 /* phys kernel start */
rlwinm r5,r5,0,~0x3ffffff /* aligned 64M */
subf r4,r5,r4 /* memstart_addr - phys kernel start */
- li r5,0 /* no device tree */
+ lis r7,KERNELBASE@h
+ ori r7,r7,KERNELBASE@l
+ cmpw r20,r7 /* if kernstart_virt_addr != KERNELBASE, randomized */
+ beq 2f
+ li r4,0
+2: li r5,0 /* no device tree */
li r6,0 /* not boot cpu */
bl restore_to_as0
@@ -1115,6 +1122,54 @@ __secondary_hold_acknowledge:
#endif
/*
+ * Create a 64M tlb by address and entry
+ * r3 - entry
+ * r4 - virtual address
+ * r5/r6 - physical address
+ */
+_GLOBAL(create_kaslr_tlb_entry)
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r6) */
+ mtspr SPRN_MAS0,r7 /* Write MAS0 */
+
+ lis r3,(MAS1_VALID|MAS1_IPROT)@h
+ ori r3,r3,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
+ mtspr SPRN_MAS1,r3 /* Write MAS1 */
+
+ lis r3,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@h
+ ori r3,r3,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@l
+ and r3,r3,r4
+ ori r3,r3,MAS2_M_IF_NEEDED@l
+ mtspr SPRN_MAS2,r3 /* Write MAS2(EPN) */
+
+#ifdef CONFIG_PHYS_64BIT
+ ori r8,r6,(MAS3_SW|MAS3_SR|MAS3_SX)
+ mtspr SPRN_MAS3,r8 /* Write MAS3(RPN) */
+ mtspr SPRN_MAS7,r5
+#else
+ ori r8,r5,(MAS3_SW|MAS3_SR|MAS3_SX)
+ mtspr SPRN_MAS3,r8 /* Write MAS3(RPN) */
+#endif
+
+ tlbwe /* Write TLB */
+ isync
+ sync
+ blr
+
+/*
+ * Return to the start of the relocated kernel and run again
+ * r3 - virtual address of fdt
+ * r4 - entry of the kernel
+ */
+_GLOBAL(reloc_kernel_entry)
+ mfmsr r7
+ rlwinm r7, r7, 0, ~(MSR_IS | MSR_DS)
+
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r7
+ rfi
+
+/*
* Create a tlb entry with the same effective and physical address as
* the tlb entry used by the current running code. But set the TS to 1.
* Then switch to the address space 1. It will return with the r3 set to
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index c4ed328a7b96..078fe3d76feb 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -86,6 +86,7 @@ void arch_crash_save_vmcoreinfo(void)
VMCOREINFO_STRUCT_SIZE(mmu_psize_def);
VMCOREINFO_OFFSET(mmu_psize_def, shift);
#endif
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
}
/*
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index ff20c253f273..1864605eca29 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -330,18 +330,13 @@ kexec_create_tlb:
rlwimi r9,r10,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r9) */
/* Set up a temp identity mapping v:0 to p:0 and return to it. */
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
-#define M_IF_NEEDED MAS2_M
-#else
-#define M_IF_NEEDED 0
-#endif
mtspr SPRN_MAS0,r9
lis r9,(MAS1_VALID|MAS1_IPROT)@h
ori r9,r9,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
mtspr SPRN_MAS1,r9
- LOAD_REG_IMMEDIATE(r9, 0x0 | M_IF_NEEDED)
+ LOAD_REG_IMMEDIATE(r9, 0x0 | MAS2_M_IF_NEEDED)
mtspr SPRN_MAS2,r9
LOAD_REG_IMMEDIATE(r9, 0x0 | MAS3_SR | MAS3_SW | MAS3_SX)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 25aaa3903000..488f1eecc0de 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -715,8 +715,28 @@ static struct notifier_block ppc_panic_block = {
.priority = INT_MIN /* may not return; must be done last */
};
+/*
+ * Dump out kernel offset information on panic.
+ */
+static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
+ void *p)
+{
+ pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
+ kaslr_offset(), KERNELBASE);
+
+ return 0;
+}
+
+static struct notifier_block kernel_offset_notifier = {
+ .notifier_call = dump_kernel_offset
+};
+
void __init setup_panic(void)
{
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0)
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &kernel_offset_notifier);
+
/* PPC64 always does a hard irq disable in its panic handler */
if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic)
return;
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index a84da92920f7..42ef7a6e6098 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -21,6 +21,13 @@
#include <asm/pgtable.h>
#include <asm/kup.h>
+phys_addr_t memstart_addr __ro_after_init = (phys_addr_t)~0ull;
+EXPORT_SYMBOL_GPL(memstart_addr);
+phys_addr_t kernstart_addr __ro_after_init;
+EXPORT_SYMBOL_GPL(kernstart_addr);
+unsigned long kernstart_virt_addr __ro_after_init = KERNELBASE;
+EXPORT_SYMBOL_GPL(kernstart_virt_addr);
+
static bool disable_kuep = !IS_ENABLED(CONFIG_PPC_KUEP);
static bool disable_kuap = !IS_ENABLED(CONFIG_PPC_KUAP);
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index b04896a88d79..872df48ae41b 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -56,11 +56,6 @@
phys_addr_t total_memory;
phys_addr_t total_lowmem;
-phys_addr_t memstart_addr = (phys_addr_t)~0ull;
-EXPORT_SYMBOL(memstart_addr);
-phys_addr_t kernstart_addr;
-EXPORT_SYMBOL(kernstart_addr);
-
#ifdef CONFIG_RELOCATABLE
/* Used in __va()/__pa() */
long long virt_phys_offset;
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 83d8c7122d13..4002ced3596f 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -63,11 +63,6 @@
#include <mm/mmu_decl.h>
-phys_addr_t memstart_addr = ~0;
-EXPORT_SYMBOL_GPL(memstart_addr);
-phys_addr_t kernstart_addr;
-EXPORT_SYMBOL_GPL(kernstart_addr);
-
#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
* Given an address within the vmemmap, determine the page that
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index c750ac9ec713..8e99649c24fc 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -139,10 +139,21 @@ extern unsigned long calc_cam_sz(unsigned long ram, unsigned long virt,
extern void adjust_total_lowmem(void);
extern int switch_to_as1(void);
extern void restore_to_as0(int esel, int offset, void *dt_ptr, int bootcpu);
+void create_kaslr_tlb_entry(int entry, unsigned long virt, phys_addr_t phys);
+void reloc_kernel_entry(void *fdt, int addr);
+extern int is_second_reloc;
#endif
extern void loadcam_entry(unsigned int index);
extern void loadcam_multi(int first_idx, int num, int tmp_idx);
+#ifdef CONFIG_RANDOMIZE_BASE
+void kaslr_early_init(void *dt_ptr, phys_addr_t size);
+void kaslr_late_init(void);
+#else
+static inline void kaslr_early_init(void *dt_ptr, phys_addr_t size) {}
+static inline void kaslr_late_init(void) {}
+#endif
+
struct tlbcam {
u32 MAS0;
u32 MAS1;
diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile
index 33b6f6f29d3f..0424f6ce5bd8 100644
--- a/arch/powerpc/mm/nohash/Makefile
+++ b/arch/powerpc/mm/nohash/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_40x) += 40x.o
obj-$(CONFIG_44x) += 44x.o
obj-$(CONFIG_PPC_8xx) += 8xx.o
obj-$(CONFIG_PPC_FSL_BOOK3E) += fsl_booke.o
+obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_booke.o
ifdef CONFIG_HUGETLB_PAGE
obj-$(CONFIG_PPC_FSL_BOOK3E) += book3e_hugetlbpage.o
endif
diff --git a/arch/powerpc/mm/nohash/fsl_booke.c b/arch/powerpc/mm/nohash/fsl_booke.c
index 556e3cd52a35..b4eb06ceb189 100644
--- a/arch/powerpc/mm/nohash/fsl_booke.c
+++ b/arch/powerpc/mm/nohash/fsl_booke.c
@@ -263,11 +263,13 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
int __initdata is_second_reloc;
notrace void __init relocate_init(u64 dt_ptr, phys_addr_t start)
{
- unsigned long base = KERNELBASE;
+ unsigned long base = kernstart_virt_addr;
+ phys_addr_t size;
kernstart_addr = start;
if (is_second_reloc) {
virt_phys_offset = PAGE_OFFSET - memstart_addr;
+ kaslr_late_init();
return;
}
@@ -291,7 +293,7 @@ notrace void __init relocate_init(u64 dt_ptr, phys_addr_t start)
start &= ~0x3ffffff;
base &= ~0x3ffffff;
virt_phys_offset = base - start;
- early_get_first_memblock_info(__va(dt_ptr), NULL);
+ early_get_first_memblock_info(__va(dt_ptr), &size);
/*
* We now get the memstart_addr, then we should check if this
* address is the same as what the PAGE_OFFSET map to now. If
@@ -316,6 +318,8 @@ notrace void __init relocate_init(u64 dt_ptr, phys_addr_t start)
/* We should never reach here */
panic("Relocation error");
}
+
+ kaslr_early_init(__va(dt_ptr), size);
}
#endif
#endif
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
new file mode 100644
index 000000000000..4a75f2d9bf0e
--- /dev/null
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -0,0 +1,401 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// Copyright (C) 2019 Jason Yan <yanaijie@huawei.com>
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/stddef.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/memblock.h>
+#include <linux/libfdt.h>
+#include <linux/crash_core.h>
+#include <asm/pgalloc.h>
+#include <asm/prom.h>
+#include <asm/kdump.h>
+#include <mm/mmu_decl.h>
+#include <generated/compile.h>
+#include <generated/utsrelease.h>
+
+struct regions {
+ unsigned long pa_start;
+ unsigned long pa_end;
+ unsigned long kernel_size;
+ unsigned long dtb_start;
+ unsigned long dtb_end;
+ unsigned long initrd_start;
+ unsigned long initrd_end;
+ unsigned long crash_start;
+ unsigned long crash_end;
+ int reserved_mem;
+ int reserved_mem_addr_cells;
+ int reserved_mem_size_cells;
+};
+
+/* Simplified build-specific string for starting entropy. */
+static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+ LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+
+struct regions __initdata regions;
+
+static __init void kaslr_get_cmdline(void *fdt)
+{
+ int node = fdt_path_offset(fdt, "/chosen");
+
+ early_init_dt_scan_chosen(node, "chosen", 1, boot_command_line);
+}
+
+static unsigned long __init rotate_xor(unsigned long hash, const void *area,
+ size_t size)
+{
+ size_t i;
+ const unsigned long *ptr = area;
+
+ for (i = 0; i < size / sizeof(hash); i++) {
+ /* Rotate by odd number of bits and XOR. */
+ hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
+ hash ^= ptr[i];
+ }
+
+ return hash;
+}
+
+/* Attempt to create a simple starting entropy. This can make it defferent for
+ * every build but it is still not enough. Stronger entropy should
+ * be added to make it change for every boot.
+ */
+static unsigned long __init get_boot_seed(void *fdt)
+{
+ unsigned long hash = 0;
+
+ hash = rotate_xor(hash, build_str, sizeof(build_str));
+ hash = rotate_xor(hash, fdt, fdt_totalsize(fdt));
+
+ return hash;
+}
+
+static __init u64 get_kaslr_seed(void *fdt)
+{
+ int node, len;
+ fdt64_t *prop;
+ u64 ret;
+
+ node = fdt_path_offset(fdt, "/chosen");
+ if (node < 0)
+ return 0;
+
+ prop = fdt_getprop_w(fdt, node, "kaslr-seed", &len);
+ if (!prop || len != sizeof(u64))
+ return 0;
+
+ ret = fdt64_to_cpu(*prop);
+ *prop = 0;
+ return ret;
+}
+
+static __init bool regions_overlap(u32 s1, u32 e1, u32 s2, u32 e2)
+{
+ return e1 >= s2 && e2 >= s1;
+}
+
+static __init bool overlaps_reserved_region(const void *fdt, u32 start,
+ u32 end)
+{
+ int subnode, len, i;
+ u64 base, size;
+
+ /* check for overlap with /memreserve/ entries */
+ for (i = 0; i < fdt_num_mem_rsv(fdt); i++) {
+ if (fdt_get_mem_rsv(fdt, i, &base, &size) < 0)
+ continue;
+ if (regions_overlap(start, end, base, base + size))
+ return true;
+ }
+
+ if (regions.reserved_mem < 0)
+ return false;
+
+ /* check for overlap with static reservations in /reserved-memory */
+ for (subnode = fdt_first_subnode(fdt, regions.reserved_mem);
+ subnode >= 0;
+ subnode = fdt_next_subnode(fdt, subnode)) {
+ const fdt32_t *reg;
+ u64 rsv_end;
+
+ len = 0;
+ reg = fdt_getprop(fdt, subnode, "reg", &len);
+ while (len >= (regions.reserved_mem_addr_cells +
+ regions.reserved_mem_size_cells)) {
+ base = fdt32_to_cpu(reg[0]);
+ if (regions.reserved_mem_addr_cells == 2)
+ base = (base << 32) | fdt32_to_cpu(reg[1]);
+
+ reg += regions.reserved_mem_addr_cells;
+ len -= 4 * regions.reserved_mem_addr_cells;
+
+ size = fdt32_to_cpu(reg[0]);
+ if (regions.reserved_mem_size_cells == 2)
+ size = (size << 32) | fdt32_to_cpu(reg[1]);
+
+ reg += regions.reserved_mem_size_cells;
+ len -= 4 * regions.reserved_mem_size_cells;
+
+ if (base >= regions.pa_end)
+ continue;
+
+ rsv_end = min(base + size, (u64)U32_MAX);
+
+ if (regions_overlap(start, end, base, rsv_end))
+ return true;
+ }
+ }
+ return false;
+}
+
+static __init bool overlaps_region(const void *fdt, u32 start,
+ u32 end)
+{
+ if (regions_overlap(start, end, __pa(_stext), __pa(_end)))
+ return true;
+
+ if (regions_overlap(start, end, regions.dtb_start,
+ regions.dtb_end))
+ return true;
+
+ if (regions_overlap(start, end, regions.initrd_start,
+ regions.initrd_end))
+ return true;
+
+ if (regions_overlap(start, end, regions.crash_start,
+ regions.crash_end))
+ return true;
+
+ return overlaps_reserved_region(fdt, start, end);
+}
+
+static void __init get_crash_kernel(void *fdt, unsigned long size)
+{
+#ifdef CONFIG_CRASH_CORE
+ unsigned long long crash_size, crash_base;
+ int ret;
+
+ ret = parse_crashkernel(boot_command_line, size, &crash_size,
+ &crash_base);
+ if (ret != 0 || crash_size == 0)
+ return;
+ if (crash_base == 0)
+ crash_base = KDUMP_KERNELBASE;
+
+ regions.crash_start = (unsigned long)crash_base;
+ regions.crash_end = (unsigned long)(crash_base + crash_size);
+
+ pr_debug("crash_base=0x%llx crash_size=0x%llx\n", crash_base, crash_size);
+#endif
+}
+
+static void __init get_initrd_range(void *fdt)
+{
+ u64 start, end;
+ int node, len;
+ const __be32 *prop;
+
+ node = fdt_path_offset(fdt, "/chosen");
+ if (node < 0)
+ return;
+
+ prop = fdt_getprop(fdt, node, "linux,initrd-start", &len);
+ if (!prop)
+ return;
+ start = of_read_number(prop, len / 4);
+
+ prop = fdt_getprop(fdt, node, "linux,initrd-end", &len);
+ if (!prop)
+ return;
+ end = of_read_number(prop, len / 4);
+
+ regions.initrd_start = (unsigned long)start;
+ regions.initrd_end = (unsigned long)end;
+
+ pr_debug("initrd_start=0x%llx initrd_end=0x%llx\n", start, end);
+}
+
+static __init unsigned long get_usable_address(const void *fdt,
+ unsigned long start,
+ unsigned long offset)
+{
+ unsigned long pa;
+ unsigned long pa_end;
+
+ for (pa = offset; (long)pa > (long)start; pa -= SZ_16K) {
+ pa_end = pa + regions.kernel_size;
+ if (overlaps_region(fdt, pa, pa_end))
+ continue;
+
+ return pa;
+ }
+ return 0;
+}
+
+static __init void get_cell_sizes(const void *fdt, int node, int *addr_cells,
+ int *size_cells)
+{
+ const int *prop;
+ int len;
+
+ /*
+ * Retrieve the #address-cells and #size-cells properties
+ * from the 'node', or use the default if not provided.
+ */
+ *addr_cells = *size_cells = 1;
+
+ prop = fdt_getprop(fdt, node, "#address-cells", &len);
+ if (len == 4)
+ *addr_cells = fdt32_to_cpu(*prop);
+ prop = fdt_getprop(fdt, node, "#size-cells", &len);
+ if (len == 4)
+ *size_cells = fdt32_to_cpu(*prop);
+}
+
+static unsigned long __init kaslr_legal_offset(void *dt_ptr, unsigned long index,
+ unsigned long offset)
+{
+ unsigned long koffset = 0;
+ unsigned long start;
+
+ while ((long)index >= 0) {
+ offset = memstart_addr + index * SZ_64M + offset;
+ start = memstart_addr + index * SZ_64M;
+ koffset = get_usable_address(dt_ptr, start, offset);
+ if (koffset)
+ break;
+ index--;
+ }
+
+ if (koffset != 0)
+ koffset -= memstart_addr;
+
+ return koffset;
+}
+
+static inline __init bool kaslr_disabled(void)
+{
+ return strstr(boot_command_line, "nokaslr") != NULL;
+}
+
+static unsigned long __init kaslr_choose_location(void *dt_ptr, phys_addr_t size,
+ unsigned long kernel_sz)
+{
+ unsigned long offset, random;
+ unsigned long ram, linear_sz;
+ u64 seed;
+ unsigned long index;
+
+ kaslr_get_cmdline(dt_ptr);
+ if (kaslr_disabled())
+ return 0;
+
+ random = get_boot_seed(dt_ptr);
+
+ seed = get_tb() << 32;
+ seed ^= get_tb();
+ random = rotate_xor(random, &seed, sizeof(seed));
+
+ /*
+ * Retrieve (and wipe) the seed from the FDT
+ */
+ seed = get_kaslr_seed(dt_ptr);
+ if (seed)
+ random = rotate_xor(random, &seed, sizeof(seed));
+ else
+ pr_warn("KASLR: No safe seed for randomizing the kernel base.\n");
+
+ ram = min_t(phys_addr_t, __max_low_memory, size);
+ ram = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, true);
+ linear_sz = min_t(unsigned long, ram, SZ_512M);
+
+ /* If the linear size is smaller than 64M, do not randmize */
+ if (linear_sz < SZ_64M)
+ return 0;
+
+ /* check for a reserved-memory node and record its cell sizes */
+ regions.reserved_mem = fdt_path_offset(dt_ptr, "/reserved-memory");
+ if (regions.reserved_mem >= 0)
+ get_cell_sizes(dt_ptr, regions.reserved_mem,
+ &regions.reserved_mem_addr_cells,
+ &regions.reserved_mem_size_cells);
+
+ regions.pa_start = memstart_addr;
+ regions.pa_end = memstart_addr + linear_sz;
+ regions.dtb_start = __pa(dt_ptr);
+ regions.dtb_end = __pa(dt_ptr) + fdt_totalsize(dt_ptr);
+ regions.kernel_size = kernel_sz;
+
+ get_initrd_range(dt_ptr);
+ get_crash_kernel(dt_ptr, ram);
+
+ /*
+ * Decide which 64M we want to start
+ * Only use the low 8 bits of the random seed
+ */
+ index = random & 0xFF;
+ index %= linear_sz / SZ_64M;
+
+ /* Decide offset inside 64M */
+ offset = random % (SZ_64M - kernel_sz);
+ offset = round_down(offset, SZ_16K);
+
+ return kaslr_legal_offset(dt_ptr, index, offset);
+}
+
+/*
+ * To see if we need to relocate the kernel to a random offset
+ * void *dt_ptr - address of the device tree
+ * phys_addr_t size - size of the first memory block
+ */
+notrace void __init kaslr_early_init(void *dt_ptr, phys_addr_t size)
+{
+ unsigned long tlb_virt;
+ phys_addr_t tlb_phys;
+ unsigned long offset;
+ unsigned long kernel_sz;
+
+ kernel_sz = (unsigned long)_end - (unsigned long)_stext;
+
+ offset = kaslr_choose_location(dt_ptr, size, kernel_sz);
+ if (offset == 0)
+ return;
+
+ kernstart_virt_addr += offset;
+ kernstart_addr += offset;
+
+ is_second_reloc = 1;
+
+ if (offset >= SZ_64M) {
+ tlb_virt = round_down(kernstart_virt_addr, SZ_64M);
+ tlb_phys = round_down(kernstart_addr, SZ_64M);
+
+ /* Create kernel map to relocate in */
+ create_kaslr_tlb_entry(1, tlb_virt, tlb_phys);
+ }
+
+ /* Copy the kernel to it's new location and run */
+ memcpy((void *)kernstart_virt_addr, (void *)_stext, kernel_sz);
+ flush_icache_range(kernstart_virt_addr, kernstart_virt_addr + kernel_sz);
+
+ reloc_kernel_entry(dt_ptr, kernstart_virt_addr);
+}
+
+void __init kaslr_late_init(void)
+{
+ /* If randomized, clear the original kernel */
+ if (kernstart_virt_addr != KERNELBASE) {
+ unsigned long kernel_sz;
+
+ kernel_sz = (unsigned long)_end - kernstart_virt_addr;
+ memzero_explicit((void *)KERNELBASE, kernel_sz);
+ }
+}