diff options
Diffstat (limited to 'arch/x86/mm/pat')
| -rw-r--r-- | arch/x86/mm/pat/cpa-test.c | 4 | ||||
| -rw-r--r-- | arch/x86/mm/pat/memtype.c | 157 | ||||
| -rw-r--r-- | arch/x86/mm/pat/set_memory.c | 123 |
3 files changed, 146 insertions, 138 deletions
diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c index 423b21e80929..3d2f7f0a6ed1 100644 --- a/arch/x86/mm/pat/cpa-test.c +++ b/arch/x86/mm/pat/cpa-test.c @@ -136,10 +136,10 @@ static int pageattr_test(void) failed += print_split(&sa); for (i = 0; i < NTEST; i++) { - unsigned long pfn = prandom_u32_max(max_pfn_mapped); + unsigned long pfn = get_random_u32_below(max_pfn_mapped); addr[i] = (unsigned long)__va(pfn << PAGE_SHIFT); - len[i] = prandom_u32_max(NPAGES); + len[i] = get_random_u32_below(NPAGES); len[i] = min_t(unsigned long, len[i], max_pfn_mapped - pfn - 1); if (len[i] == 0) diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 66a209f7eb86..46de9cf5c91d 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -43,6 +43,7 @@ #include <linux/rbtree.h> #include <asm/cacheflush.h> +#include <asm/cacheinfo.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> @@ -60,41 +61,34 @@ #undef pr_fmt #define pr_fmt(fmt) "" fmt -static bool __read_mostly pat_bp_initialized; static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT); -static bool __initdata pat_force_disabled = !IS_ENABLED(CONFIG_X86_PAT); -static bool __read_mostly pat_bp_enabled; -static bool __read_mostly pat_cm_initialized; +static u64 __ro_after_init pat_msr_val; /* * PAT support is enabled by default, but can be disabled for * various user-requested or hardware-forced reasons: */ -void pat_disable(const char *msg_reason) +static void __init pat_disable(const char *msg_reason) { if (pat_disabled) return; - if (pat_bp_initialized) { - WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); - return; - } - pat_disabled = true; pr_info("x86/PAT: %s\n", msg_reason); + + memory_caching_control &= ~CACHE_PAT; } static int __init nopat(char *str) { pat_disable("PAT support disabled via boot option."); - pat_force_disabled = true; return 0; } early_param("nopat", nopat); bool pat_enabled(void) { - return pat_bp_enabled; + return !pat_disabled; } EXPORT_SYMBOL_GPL(pat_enabled); @@ -192,7 +186,8 @@ enum { #define CM(c) (_PAGE_CACHE_MODE_ ## c) -static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) +static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val, + char *msg) { enum page_cache_mode cache; char *cache_mode; @@ -219,14 +214,12 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -static void __init_cache_modes(u64 pat) +static void __init init_cache_modes(u64 pat) { enum page_cache_mode cache; char pat_msg[33]; int i; - WARN_ON_ONCE(pat_cm_initialized); - pat_msg[32] = 0; for (i = 7; i >= 0; i--) { cache = pat_get_cache_mode((pat >> (i * 8)) & 7, @@ -234,34 +227,9 @@ static void __init_cache_modes(u64 pat) update_cache_mode_entry(i, cache); } pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); - - pat_cm_initialized = true; } -#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) - -static void pat_bp_init(u64 pat) -{ - u64 tmp_pat; - - if (!boot_cpu_has(X86_FEATURE_PAT)) { - pat_disable("PAT not supported by the CPU."); - return; - } - - rdmsrl(MSR_IA32_CR_PAT, tmp_pat); - if (!tmp_pat) { - pat_disable("PAT support disabled by the firmware."); - return; - } - - wrmsrl(MSR_IA32_CR_PAT, pat); - pat_bp_enabled = true; - - __init_cache_modes(pat); -} - -static void pat_ap_init(u64 pat) +void pat_cpu_init(void) { if (!boot_cpu_has(X86_FEATURE_PAT)) { /* @@ -271,30 +239,39 @@ static void pat_ap_init(u64 pat) panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n"); } - wrmsrl(MSR_IA32_CR_PAT, pat); + wrmsrl(MSR_IA32_CR_PAT, pat_msr_val); } -void __init init_cache_modes(void) +/** + * pat_bp_init - Initialize the PAT MSR value and PAT table + * + * This function initializes PAT MSR value and PAT table with an OS-defined + * value to enable additional cache attributes, WC, WT and WP. + * + * This function prepares the calls of pat_cpu_init() via cache_cpu_init() + * on all CPUs. + */ +void __init pat_bp_init(void) { - u64 pat = 0; + struct cpuinfo_x86 *c = &boot_cpu_data; +#define PAT(p0, p1, p2, p3, p4, p5, p6, p7) \ + (((u64)PAT_ ## p0) | ((u64)PAT_ ## p1 << 8) | \ + ((u64)PAT_ ## p2 << 16) | ((u64)PAT_ ## p3 << 24) | \ + ((u64)PAT_ ## p4 << 32) | ((u64)PAT_ ## p5 << 40) | \ + ((u64)PAT_ ## p6 << 48) | ((u64)PAT_ ## p7 << 56)) - if (pat_cm_initialized) - return; - if (boot_cpu_has(X86_FEATURE_PAT)) { - /* - * CPU supports PAT. Set PAT table to be consistent with - * PAT MSR. This case supports "nopat" boot option, and - * virtual machine environments which support PAT without - * MTRRs. In specific, Xen has unique setup to PAT MSR. - * - * If PAT MSR returns 0, it is considered invalid and emulates - * as No PAT. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - } + if (!IS_ENABLED(CONFIG_X86_PAT)) + pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); + + if (!cpu_feature_enabled(X86_FEATURE_PAT)) + pat_disable("PAT not supported by the CPU."); + else + rdmsrl(MSR_IA32_CR_PAT, pat_msr_val); + + if (!pat_msr_val) { + pat_disable("PAT support disabled by the firmware."); - if (!pat) { /* * No PAT. Emulate the PAT table that corresponds to the two * cache bits, PWT (Write Through) and PCD (Cache Disable). @@ -313,40 +290,22 @@ void __init init_cache_modes(void) * NOTE: When WC or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); - } else if (!pat_force_disabled && cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) { - /* - * Clearly PAT is enabled underneath. Allow pat_enabled() to - * reflect this. - */ - pat_bp_enabled = true; + pat_msr_val = PAT(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC); } - __init_cache_modes(pat); -} - -/** - * pat_init - Initialize the PAT MSR and PAT table on the current CPU - * - * This function initializes PAT MSR and PAT table with an OS-defined value - * to enable additional cache attributes, WC, WT and WP. - * - * This function must be called on all CPUs using the specific sequence of - * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this - * procedure for PAT. - */ -void pat_init(void) -{ - u64 pat; - struct cpuinfo_x86 *c = &boot_cpu_data; - -#ifndef CONFIG_X86_PAT - pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); -#endif - - if (pat_disabled) + /* + * Xen PV doesn't allow to set PAT MSR, but all cache modes are + * supported. + * When running as TDX guest setting the PAT MSR won't work either + * due to the requirement to set CR0.CD when doing so. Rely on + * firmware to have set the PAT MSR correctly. + */ + if (pat_disabled || + cpu_feature_enabled(X86_FEATURE_XENPV) || + cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + init_cache_modes(pat_msr_val); return; + } if ((c->x86_vendor == X86_VENDOR_INTEL) && (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || @@ -371,8 +330,7 @@ void pat_init(void) * NOTE: When WT or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); + pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC); } else { /* * Full PAT support. We put WT in slot 7 to improve @@ -400,19 +358,14 @@ void pat_init(void) * The reserved slots are unused, but mapped to their * corresponding types in the presence of PAT errata. */ - pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WP) | PAT(6, UC_MINUS) | PAT(7, WT); + pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT); } - if (!pat_bp_initialized) { - pat_bp_init(pat); - pat_bp_initialized = true; - } else { - pat_ap_init(pat); - } -} + memory_caching_control |= CACHE_PAT; + init_cache_modes(pat_msr_val); #undef PAT +} static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */ diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 2e5a045731de..356758b7d4b4 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <linux/cc_platform.h> #include <linux/set_memory.h> +#include <linux/memregion.h> #include <asm/e820/api.h> #include <asm/processor.h> @@ -219,6 +220,23 @@ within_inclusive(unsigned long addr, unsigned long start, unsigned long end) #ifdef CONFIG_X86_64 +/* + * The kernel image is mapped into two places in the virtual address space + * (addresses without KASLR, of course): + * + * 1. The kernel direct map (0xffff880000000000) + * 2. The "high kernel map" (0xffffffff81000000) + * + * We actually execute out of #2. If we get the address of a kernel symbol, it + * points to #2, but almost all physical-to-virtual translations point to #1. + * + * This is so that we can have both a directmap of all physical memory *and* + * take full advantage of the the limited (s32) immediate addressing range (2G) + * of x86_64. + * + * See Documentation/x86/x86_64/mm.rst for more detail. + */ + static inline unsigned long highmap_start_pfn(void) { return __pa_symbol(_text) >> PAGE_SHIFT; @@ -330,6 +348,23 @@ void arch_invalidate_pmem(void *addr, size_t size) EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif +#ifdef CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION +bool cpu_cache_has_invalidate_memregion(void) +{ + return !cpu_feature_enabled(X86_FEATURE_HYPERVISOR); +} +EXPORT_SYMBOL_NS_GPL(cpu_cache_has_invalidate_memregion, DEVMEM); + +int cpu_cache_invalidate_memregion(int res_desc) +{ + if (WARN_ON_ONCE(!cpu_cache_has_invalidate_memregion())) + return -ENXIO; + wbinvd_on_all_cpus(); + return 0; +} +EXPORT_SYMBOL_NS_GPL(cpu_cache_invalidate_memregion, DEVMEM); +#endif + static void __cpa_flush_all(void *arg) { unsigned long cache = (unsigned long)arg; @@ -587,10 +622,6 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star { unsigned long end; - /* Kernel text is rw at boot up */ - if (system_state == SYSTEM_BOOTING) - return new; - /* * 32-bit has some unfixable W+X issues, like EFI code * and writeable data being in the same page. Disable @@ -747,11 +778,11 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) switch (level) { case PG_LEVEL_1G: phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; - offset = virt_addr & ~PUD_PAGE_MASK; + offset = virt_addr & ~PUD_MASK; break; case PG_LEVEL_2M: phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; - offset = virt_addr & ~PMD_PAGE_MASK; + offset = virt_addr & ~PMD_MASK; break; default: phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; @@ -1041,7 +1072,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, case PG_LEVEL_1G: ref_prot = pud_pgprot(*(pud_t *)kpte); ref_pfn = pud_pfn(*(pud_t *)kpte); - pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; + pfninc = PMD_SIZE >> PAGE_SHIFT; lpaddr = address & PUD_MASK; lpinc = PMD_SIZE; /* @@ -1628,8 +1659,11 @@ repeat: return err; } -static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias); +static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary); +/* + * Check the directmap and "high kernel map" 'aliases'. + */ static int cpa_process_alias(struct cpa_data *cpa) { struct cpa_data alias_cpa; @@ -1653,6 +1687,12 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + /* Directmap always has NX set, do not modify. */ + if (__supported_pte_mask & _PAGE_NX) { + alias_cpa.mask_clr.pgprot &= ~_PAGE_NX; + alias_cpa.mask_set.pgprot &= ~_PAGE_NX; + } + cpa->force_flush_all = 1; ret = __change_page_attr_set_clr(&alias_cpa, 0); @@ -1675,6 +1715,15 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + /* + * [_text, _brk_end) also covers data, do not modify NX except + * in cases where the highmap is the primary target. + */ + if (__supported_pte_mask & _PAGE_NX) { + alias_cpa.mask_clr.pgprot &= ~_PAGE_NX; + alias_cpa.mask_set.pgprot &= ~_PAGE_NX; + } + cpa->force_flush_all = 1; /* * The high mapping range is imprecise, so ignore the @@ -1687,12 +1736,19 @@ static int cpa_process_alias(struct cpa_data *cpa) return 0; } -static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) +static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary) { unsigned long numpages = cpa->numpages; unsigned long rempages = numpages; int ret = 0; + /* + * No changes, easy! + */ + if (!(pgprot_val(cpa->mask_set) | pgprot_val(cpa->mask_clr)) && + !cpa->force_split) + return ret; + while (rempages) { /* * Store the remaining nr of pages for the large page @@ -1705,13 +1761,13 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) if (!debug_pagealloc_enabled()) spin_lock(&cpa_lock); - ret = __change_page_attr(cpa, checkalias); + ret = __change_page_attr(cpa, primary); if (!debug_pagealloc_enabled()) spin_unlock(&cpa_lock); if (ret) goto out; - if (checkalias) { + if (primary && !(cpa->flags & CPA_NO_CHECK_ALIAS)) { ret = cpa_process_alias(cpa); if (ret) goto out; @@ -1739,7 +1795,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, struct page **pages) { struct cpa_data cpa; - int ret, cache, checkalias; + int ret, cache; memset(&cpa, 0, sizeof(cpa)); @@ -1785,20 +1841,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, cpa.numpages = numpages; cpa.mask_set = mask_set; cpa.mask_clr = mask_clr; - cpa.flags = 0; + cpa.flags = in_flag; cpa.curpage = 0; cpa.force_split = force_split; - if (in_flag & (CPA_ARRAY | CPA_PAGES_ARRAY)) - cpa.flags |= in_flag; - - /* No alias checking for _NX bit modifications */ - checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX; - /* Has caller explicitly disabled alias checking? */ - if (in_flag & CPA_NO_CHECK_ALIAS) - checkalias = 0; - - ret = __change_page_attr_set_clr(&cpa, checkalias); + ret = __change_page_attr_set_clr(&cpa, 1); /* * Check whether we really changed something: @@ -2029,6 +2076,16 @@ int set_memory_ro(unsigned long addr, int numpages) return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW), 0); } +int set_memory_rox(unsigned long addr, int numpages) +{ + pgprot_t clr = __pgprot(_PAGE_RW); + + if (__supported_pte_mask & _PAGE_NX) + clr.pgprot |= _PAGE_NX; + + return change_page_attr_clear(&addr, numpages, clr, 0); +} + int set_memory_rw(unsigned long addr, int numpages) { return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0); @@ -2041,11 +2098,9 @@ int set_memory_np(unsigned long addr, int numpages) int set_memory_np_noalias(unsigned long addr, int numpages) { - int cpa_flags = CPA_NO_CHECK_ALIAS; - return change_page_attr_set_clr(&addr, numpages, __pgprot(0), __pgprot(_PAGE_PRESENT), 0, - cpa_flags, NULL); + CPA_NO_CHECK_ALIAS, NULL); } int set_memory_4k(unsigned long addr, int numpages) @@ -2262,7 +2317,7 @@ static int __set_pages_p(struct page *page, int numpages) .numpages = numpages, .mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW), .mask_clr = __pgprot(0), - .flags = 0}; + .flags = CPA_NO_CHECK_ALIAS }; /* * No alias checking needed for setting present flag. otherwise, @@ -2270,7 +2325,7 @@ static int __set_pages_p(struct page *page, int numpages) * mappings (this adds to complexity if we want to do this from * atomic context especially). Let's keep it simple! */ - return __change_page_attr_set_clr(&cpa, 0); + return __change_page_attr_set_clr(&cpa, 1); } static int __set_pages_np(struct page *page, int numpages) @@ -2281,7 +2336,7 @@ static int __set_pages_np(struct page *page, int numpages) .numpages = numpages, .mask_set = __pgprot(0), .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), - .flags = 0}; + .flags = CPA_NO_CHECK_ALIAS }; /* * No alias checking needed for setting not present flag. otherwise, @@ -2289,7 +2344,7 @@ static int __set_pages_np(struct page *page, int numpages) * mappings (this adds to complexity if we want to do this from * atomic context especially). Let's keep it simple! */ - return __change_page_attr_set_clr(&cpa, 0); + return __change_page_attr_set_clr(&cpa, 1); } int set_direct_map_invalid_noflush(struct page *page) @@ -2360,7 +2415,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, .numpages = numpages, .mask_set = __pgprot(0), .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)), - .flags = 0, + .flags = CPA_NO_CHECK_ALIAS, }; WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP"); @@ -2373,7 +2428,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags); - retval = __change_page_attr_set_clr(&cpa, 0); + retval = __change_page_attr_set_clr(&cpa, 1); __flush_tlb_all(); out: @@ -2403,12 +2458,12 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, .numpages = numpages, .mask_set = __pgprot(0), .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), - .flags = 0, + .flags = CPA_NO_CHECK_ALIAS, }; WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP"); - retval = __change_page_attr_set_clr(&cpa, 0); + retval = __change_page_attr_set_clr(&cpa, 1); __flush_tlb_all(); return retval; |