From 151fecfb72a0d602dfe79790602ef64b4e241574 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 19 Feb 2024 01:51:07 +0000
Subject: [PATCH] export RK_PA3
---
kernel/arch/x86/mm/ioremap.c | 225 ++++++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 170 insertions(+), 55 deletions(-)
diff --git a/kernel/arch/x86/mm/ioremap.c b/kernel/arch/x86/mm/ioremap.c
index adc7790..88cb537 100644
--- a/kernel/arch/x86/mm/ioremap.c
+++ b/kernel/arch/x86/mm/ioremap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Re-map IO memory to kernel address space so that we can access it.
* This is needed for high PCI addresses that aren't mapped in the
@@ -6,7 +7,7 @@
* (C) Copyright 1995 1996 Linus Torvalds
*/
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/ioport.h>
@@ -15,21 +16,24 @@
#include <linux/mmiotrace.h>
#include <linux/mem_encrypt.h>
#include <linux/efi.h>
+#include <linux/pgtable.h>
#include <asm/set_memory.h>
#include <asm/e820/api.h>
+#include <asm/efi.h>
#include <asm/fixmap.h>
-#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
#include <asm/setup.h>
#include "physaddr.h"
-struct ioremap_mem_flags {
- bool system_ram;
- bool desc_other;
+/*
+ * Descriptor controlling ioremap() behavior.
+ */
+struct ioremap_desc {
+ unsigned int flags;
};
/*
@@ -61,13 +65,14 @@
return err;
}
-static bool __ioremap_check_ram(struct resource *res)
+/* Does the range (or a subset of) contain normal RAM? */
+static unsigned int __ioremap_check_ram(struct resource *res)
{
unsigned long start_pfn, stop_pfn;
unsigned long i;
if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM)
- return false;
+ return 0;
start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT;
stop_pfn = (res->end + 1) >> PAGE_SHIFT;
@@ -75,45 +80,84 @@
for (i = 0; i < (stop_pfn - start_pfn); ++i)
if (pfn_valid(start_pfn + i) &&
!PageReserved(pfn_to_page(start_pfn + i)))
- return true;
+ return IORES_MAP_SYSTEM_RAM;
}
- return false;
+ return 0;
}
-static int __ioremap_check_desc_other(struct resource *res)
+/*
+ * In a SEV guest, NONE and RESERVED should not be mapped encrypted because
+ * there the whole memory is already encrypted.
+ */
+static unsigned int __ioremap_check_encrypted(struct resource *res)
{
- return (res->desc != IORES_DESC_NONE);
+ if (!sev_active())
+ return 0;
+
+ switch (res->desc) {
+ case IORES_DESC_NONE:
+ case IORES_DESC_RESERVED:
+ break;
+ default:
+ return IORES_MAP_ENCRYPTED;
+ }
+
+ return 0;
}
-static int __ioremap_res_check(struct resource *res, void *arg)
+/*
+ * The EFI runtime services data area is not covered by walk_mem_res(), but must
+ * be mapped encrypted when SEV is active.
+ */
+static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *desc)
{
- struct ioremap_mem_flags *flags = arg;
+ if (!sev_active())
+ return;
- if (!flags->system_ram)
- flags->system_ram = __ioremap_check_ram(res);
+ if (!IS_ENABLED(CONFIG_EFI))
+ return;
- if (!flags->desc_other)
- flags->desc_other = __ioremap_check_desc_other(res);
+ if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA ||
+ (efi_mem_type(addr) == EFI_BOOT_SERVICES_DATA &&
+ efi_mem_attributes(addr) & EFI_MEMORY_RUNTIME))
+ desc->flags |= IORES_MAP_ENCRYPTED;
+}
- return flags->system_ram && flags->desc_other;
+static int __ioremap_collect_map_flags(struct resource *res, void *arg)
+{
+ struct ioremap_desc *desc = arg;
+
+ if (!(desc->flags & IORES_MAP_SYSTEM_RAM))
+ desc->flags |= __ioremap_check_ram(res);
+
+ if (!(desc->flags & IORES_MAP_ENCRYPTED))
+ desc->flags |= __ioremap_check_encrypted(res);
+
+ return ((desc->flags & (IORES_MAP_SYSTEM_RAM | IORES_MAP_ENCRYPTED)) ==
+ (IORES_MAP_SYSTEM_RAM | IORES_MAP_ENCRYPTED));
}
/*
* To avoid multiple resource walks, this function walks resources marked as
* IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a
* resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES).
+ *
+ * After that, deal with misc other ranges in __ioremap_check_other() which do
+ * not fall into the above category.
*/
static void __ioremap_check_mem(resource_size_t addr, unsigned long size,
- struct ioremap_mem_flags *flags)
+ struct ioremap_desc *desc)
{
u64 start, end;
start = (u64)addr;
end = start + size - 1;
- memset(flags, 0, sizeof(*flags));
+ memset(desc, 0, sizeof(struct ioremap_desc));
- walk_mem_res(start, end, flags, __ioremap_res_check);
+ walk_mem_res(start, end, desc, __ioremap_collect_map_flags);
+
+ __ioremap_check_other(addr, desc);
}
/*
@@ -130,14 +174,15 @@
* have to convert them into an offset in a page-aligned mapping, but the
* caller shouldn't need to know that small detail.
*/
-static void __iomem *__ioremap_caller(resource_size_t phys_addr,
- unsigned long size, enum page_cache_mode pcm, void *caller)
+static void __iomem *
+__ioremap_caller(resource_size_t phys_addr, unsigned long size,
+ enum page_cache_mode pcm, void *caller, bool encrypted)
{
unsigned long offset, vaddr;
resource_size_t last_addr;
const resource_size_t unaligned_phys_addr = phys_addr;
const unsigned long unaligned_size = size;
- struct ioremap_mem_flags mem_flags;
+ struct ioremap_desc io_desc;
struct vm_struct *area;
enum page_cache_mode new_pcm;
pgprot_t prot;
@@ -156,12 +201,12 @@
return NULL;
}
- __ioremap_check_mem(phys_addr, size, &mem_flags);
+ __ioremap_check_mem(phys_addr, size, &io_desc);
/*
* Don't allow anybody to remap normal RAM that we're using..
*/
- if (mem_flags.system_ram) {
+ if (io_desc.flags & IORES_MAP_SYSTEM_RAM) {
WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
&phys_addr, &last_addr);
return NULL;
@@ -171,13 +216,19 @@
* Mappings have to be page-aligned
*/
offset = phys_addr & ~PAGE_MASK;
- phys_addr &= PHYSICAL_PAGE_MASK;
+ phys_addr &= PAGE_MASK;
size = PAGE_ALIGN(last_addr+1) - phys_addr;
- retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
+ /*
+ * Mask out any bits not part of the actual physical
+ * address, like memory encryption bits.
+ */
+ phys_addr &= PHYSICAL_PAGE_MASK;
+
+ retval = memtype_reserve(phys_addr, (u64)phys_addr + size,
pcm, &new_pcm);
if (retval) {
- printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval);
+ printk(KERN_ERR "ioremap memtype_reserve failed %d\n", retval);
return NULL;
}
@@ -199,7 +250,7 @@
* resulting mapping.
*/
prot = PAGE_KERNEL_IO;
- if (sev_active() && mem_flags.desc_other)
+ if ((io_desc.flags & IORES_MAP_ENCRYPTED) || encrypted)
prot = pgprot_encrypted(prot);
switch (pcm) {
@@ -233,7 +284,7 @@
area->phys_addr = phys_addr;
vaddr = (unsigned long) area->addr;
- if (kernel_map_sync_memtype(phys_addr, size, pcm))
+ if (memtype_kernel_map_sync(phys_addr, size, pcm))
goto err_free_area;
if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
@@ -253,16 +304,16 @@
err_free_area:
free_vm_area(area);
err_free_memtype:
- free_memtype(phys_addr, phys_addr + size);
+ memtype_free(phys_addr, phys_addr + size);
return NULL;
}
/**
- * ioremap_nocache - map bus memory into CPU space
+ * ioremap - map bus memory into CPU space
* @phys_addr: bus address of the memory
* @size: size of the resource to map
*
- * ioremap_nocache performs a platform specific sequence of operations to
+ * ioremap performs a platform specific sequence of operations to
* make bus memory CPU accessible via the readb/readw/readl/writeb/
* writew/writel functions and the other mmio helpers. The returned
* address is not guaranteed to be usable directly as a virtual
@@ -278,7 +329,7 @@
*
* Must be freed with iounmap.
*/
-void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
+void __iomem *ioremap(resource_size_t phys_addr, unsigned long size)
{
/*
* Ideally, this should be:
@@ -291,9 +342,9 @@
enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
return __ioremap_caller(phys_addr, size, pcm,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
-EXPORT_SYMBOL(ioremap_nocache);
+EXPORT_SYMBOL(ioremap);
/**
* ioremap_uc - map bus memory into CPU space as strongly uncachable
@@ -324,7 +375,7 @@
enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC;
return __ioremap_caller(phys_addr, size, pcm,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL_GPL(ioremap_uc);
@@ -341,7 +392,7 @@
void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
{
return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_wc);
@@ -358,14 +409,21 @@
void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size)
{
return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_wt);
+
+void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size)
+{
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
+ __builtin_return_address(0), true);
+}
+EXPORT_SYMBOL(ioremap_encrypted);
void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
{
return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_cache);
@@ -374,7 +432,7 @@
{
return __ioremap_caller(phys_addr, size,
pgprot2cachemode(__pgprot(prot_val)),
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_prot);
@@ -422,7 +480,7 @@
return;
}
- free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p));
+ memtype_free(p->phys_addr, p->phys_addr + get_vm_area_size(p));
/* Finally remove it */
o = remove_vm_area((void __force *)addr);
@@ -430,6 +488,11 @@
kfree(p);
}
EXPORT_SYMBOL(iounmap);
+
+int __init arch_ioremap_p4d_supported(void)
+{
+ return 0;
+}
int __init arch_ioremap_pud_supported(void)
{
@@ -519,7 +582,7 @@
/* For SEV, these areas are encrypted */
if (sev_active())
break;
- /* Fallthrough */
+ fallthrough;
case E820_TYPE_PRAM:
return true;
@@ -576,6 +639,7 @@
static bool memremap_is_setup_data(resource_size_t phys_addr,
unsigned long size)
{
+ struct setup_indirect *indirect;
struct setup_data *data;
u64 paddr, paddr_next;
@@ -588,9 +652,35 @@
data = memremap(paddr, sizeof(*data),
MEMREMAP_WB | MEMREMAP_DEC);
+ if (!data) {
+ pr_warn("failed to memremap setup_data entry\n");
+ return false;
+ }
paddr_next = data->next;
len = data->len;
+
+ if ((phys_addr > paddr) && (phys_addr < (paddr + len))) {
+ memunmap(data);
+ return true;
+ }
+
+ if (data->type == SETUP_INDIRECT) {
+ memunmap(data);
+ data = memremap(paddr, sizeof(*data) + len,
+ MEMREMAP_WB | MEMREMAP_DEC);
+ if (!data) {
+ pr_warn("failed to memremap indirect setup_data\n");
+ return false;
+ }
+
+ indirect = (struct setup_indirect *)data->data;
+
+ if (indirect->type != SETUP_INDIRECT) {
+ paddr = indirect->addr;
+ len = indirect->len;
+ }
+ }
memunmap(data);
@@ -610,22 +700,51 @@
static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
unsigned long size)
{
+ struct setup_indirect *indirect;
struct setup_data *data;
u64 paddr, paddr_next;
paddr = boot_params.hdr.setup_data;
while (paddr) {
- unsigned int len;
+ unsigned int len, size;
if (phys_addr == paddr)
return true;
data = early_memremap_decrypted(paddr, sizeof(*data));
+ if (!data) {
+ pr_warn("failed to early memremap setup_data entry\n");
+ return false;
+ }
+
+ size = sizeof(*data);
paddr_next = data->next;
len = data->len;
- early_memunmap(data, sizeof(*data));
+ if ((phys_addr > paddr) && (phys_addr < (paddr + len))) {
+ early_memunmap(data, sizeof(*data));
+ return true;
+ }
+
+ if (data->type == SETUP_INDIRECT) {
+ size += len;
+ early_memunmap(data, sizeof(*data));
+ data = early_memremap_decrypted(paddr, size);
+ if (!data) {
+ pr_warn("failed to early memremap indirect setup_data\n");
+ return false;
+ }
+
+ indirect = (struct setup_indirect *)data->data;
+
+ if (indirect->type != SETUP_INDIRECT) {
+ paddr = indirect->addr;
+ len = indirect->len;
+ }
+ }
+
+ early_memunmap(data, size);
if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
return true;
@@ -712,10 +831,8 @@
void __init *early_memremap_encrypted_wp(resource_size_t phys_addr,
unsigned long size)
{
- /* Be sure the write-protect PAT entry is set for write-protect */
- if (__pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] != _PAGE_CACHE_MODE_WP)
+ if (!x86_has_pat_wp())
return NULL;
-
return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC_WP);
}
@@ -733,10 +850,8 @@
void __init *early_memremap_decrypted_wp(resource_size_t phys_addr,
unsigned long size)
{
- /* Be sure the write-protect PAT entry is set for write-protect */
- if (__pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] != _PAGE_CACHE_MODE_WP)
+ if (!x86_has_pat_wp())
return NULL;
-
return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC_WP);
}
#endif /* CONFIG_AMD_MEM_ENCRYPT */
@@ -817,11 +932,11 @@
pte = early_ioremap_pte(addr);
/* Sanitize 'prot' against any unsupported bits: */
- pgprot_val(flags) &= __default_kernel_pte_mask;
+ pgprot_val(flags) &= __supported_pte_mask;
if (pgprot_val(flags))
set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
else
pte_clear(&init_mm, addr, pte);
- __flush_tlb_one_kernel(addr);
+ flush_tlb_one_kernel(addr);
}
--
Gitblit v1.6.2