mirror of
				https://github.com/go-gitea/gitea.git
				synced 2025-10-31 19:06:18 +01:00 
			
		
		
		
	Refactor git command package to improve security and maintainability (#22678)
This PR follows #21535 (and replace #22592) ## Review without space diff https://github.com/go-gitea/gitea/pull/22678/files?diff=split&w=1 ## Purpose of this PR 1. Make git module command completely safe (risky user inputs won't be passed as argument option anymore) 2. Avoid low-level mistakes like https://github.com/go-gitea/gitea/pull/22098#discussion_r1045234918 3. Remove deprecated and dirty `CmdArgCheck` function, hide the `CmdArg` type 4. Simplify code when using git command ## The main idea of this PR * Move the `git.CmdArg` to the `internal` package, then no other package except `git` could use it. Then developers could never do `AddArguments(git.CmdArg(userInput))` any more. * Introduce `git.ToTrustedCmdArgs`, it's for user-provided and already trusted arguments. It's only used in a few cases, for example: use git arguments from config file, help unit test with some arguments. * Introduce `AddOptionValues` and `AddOptionFormat`, they make code more clear and simple: * Before: `AddArguments("-m").AddDynamicArguments(message)` * After: `AddOptionValues("-m", message)` * - * Before: `AddArguments(git.CmdArg(fmt.Sprintf("--author='%s <%s>'", sig.Name, sig.Email)))` * After: `AddOptionFormat("--author='%s <%s>'", sig.Name, sig.Email)` ## FAQ ### Why these changes were not done in #21535 ? #21535 is mainly a search&replace, it did its best to not change too much logic. Making the framework better needs a lot of changes, so this separate PR is needed as the second step. ### The naming of `AddOptionXxx` According to git's manual, the `--xxx` part is called `option`. ### How can it guarantee that `internal.CmdArg` won't be not misused? Go's specification guarantees that. Trying to access other package's internal package causes compilation error. And, `golangci-lint` also denies the git/internal package. Only the `git/command.go` can use it carefully. ### There is still a `ToTrustedCmdArgs`, will it still allow developers to make mistakes and pass untrusted arguments? Generally speaking, no. Because when using `ToTrustedCmdArgs`, the code will be very complex (see the changes for examples). Then developers and reviewers can know that something might be unreasonable. ### Why there was a `CmdArgCheck` and why it's removed? At the moment of #21535, to reduce unnecessary changes, `CmdArgCheck` was introduced as a hacky patch. Now, almost all code could be written as `cmd := NewCommand(); cmd.AddXxx(...)`, then there is no need for `CmdArgCheck` anymore. ### Why many codes for `signArg == ""` is deleted? Because in the old code, `signArg` could never be empty string, it's either `-S[key-id]` or `--no-gpg-sign`. So the `signArg == ""` is just dead code. --------- Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
This commit is contained in:
		| @@ -16,14 +16,20 @@ import ( | ||||
| 	"time" | ||||
| 	"unsafe" | ||||
|  | ||||
| 	"code.gitea.io/gitea/modules/git/internal" //nolint:depguard // only this file can use the internal type CmdArg, other files and packages should use AddXxx functions | ||||
| 	"code.gitea.io/gitea/modules/log" | ||||
| 	"code.gitea.io/gitea/modules/process" | ||||
| 	"code.gitea.io/gitea/modules/util" | ||||
| ) | ||||
|  | ||||
| // TrustedCmdArgs returns the trusted arguments for git command. | ||||
| // It's mainly for passing user-provided and trusted arguments to git command | ||||
| // In most cases, it shouldn't be used. Use AddXxx function instead | ||||
| type TrustedCmdArgs []internal.CmdArg | ||||
|  | ||||
| var ( | ||||
| 	// globalCommandArgs global command args for external package setting | ||||
| 	globalCommandArgs []CmdArg | ||||
| 	globalCommandArgs TrustedCmdArgs | ||||
|  | ||||
| 	// defaultCommandExecutionTimeout default command execution timeout duration | ||||
| 	defaultCommandExecutionTimeout = 360 * time.Second | ||||
| @@ -42,8 +48,6 @@ type Command struct { | ||||
| 	brokenArgs       []string | ||||
| } | ||||
|  | ||||
| type CmdArg string | ||||
|  | ||||
| func (c *Command) String() string { | ||||
| 	if len(c.args) == 0 { | ||||
| 		return c.name | ||||
| @@ -53,7 +57,7 @@ func (c *Command) String() string { | ||||
|  | ||||
| // NewCommand creates and returns a new Git Command based on given command and arguments. | ||||
| // Each argument should be safe to be trusted. User-provided arguments should be passed to AddDynamicArguments instead. | ||||
| func NewCommand(ctx context.Context, args ...CmdArg) *Command { | ||||
| func NewCommand(ctx context.Context, args ...internal.CmdArg) *Command { | ||||
| 	// Make an explicit copy of globalCommandArgs, otherwise append might overwrite it | ||||
| 	cargs := make([]string, 0, len(globalCommandArgs)+len(args)) | ||||
| 	for _, arg := range globalCommandArgs { | ||||
| @@ -70,15 +74,9 @@ func NewCommand(ctx context.Context, args ...CmdArg) *Command { | ||||
| 	} | ||||
| } | ||||
|  | ||||
| // NewCommandNoGlobals creates and returns a new Git Command based on given command and arguments only with the specify args and don't care global command args | ||||
| // Each argument should be safe to be trusted. User-provided arguments should be passed to AddDynamicArguments instead. | ||||
| func NewCommandNoGlobals(args ...CmdArg) *Command { | ||||
| 	return NewCommandContextNoGlobals(DefaultContext, args...) | ||||
| } | ||||
|  | ||||
| // NewCommandContextNoGlobals creates and returns a new Git Command based on given command and arguments only with the specify args and don't care global command args | ||||
| // Each argument should be safe to be trusted. User-provided arguments should be passed to AddDynamicArguments instead. | ||||
| func NewCommandContextNoGlobals(ctx context.Context, args ...CmdArg) *Command { | ||||
| func NewCommandContextNoGlobals(ctx context.Context, args ...internal.CmdArg) *Command { | ||||
| 	cargs := make([]string, 0, len(args)) | ||||
| 	for _, arg := range args { | ||||
| 		cargs = append(cargs, string(arg)) | ||||
| @@ -96,27 +94,70 @@ func (c *Command) SetParentContext(ctx context.Context) *Command { | ||||
| 	return c | ||||
| } | ||||
|  | ||||
| // SetDescription sets the description for this command which be returned on | ||||
| // c.String() | ||||
| // SetDescription sets the description for this command which be returned on c.String() | ||||
| func (c *Command) SetDescription(desc string) *Command { | ||||
| 	c.desc = desc | ||||
| 	return c | ||||
| } | ||||
|  | ||||
| // AddArguments adds new git argument(s) to the command. Each argument must be safe to be trusted. | ||||
| // User-provided arguments should be passed to AddDynamicArguments instead. | ||||
| func (c *Command) AddArguments(args ...CmdArg) *Command { | ||||
| // isSafeArgumentValue checks if the argument is safe to be used as a value (not an option) | ||||
| func isSafeArgumentValue(s string) bool { | ||||
| 	return s == "" || s[0] != '-' | ||||
| } | ||||
|  | ||||
| // isValidArgumentOption checks if the argument is a valid option (starting with '-'). | ||||
| // It doesn't check whether the option is supported or not | ||||
| func isValidArgumentOption(s string) bool { | ||||
| 	return s != "" && s[0] == '-' | ||||
| } | ||||
|  | ||||
| // AddArguments adds new git arguments (option/value) to the command. It only accepts string literals, or trusted CmdArg. | ||||
| // Type CmdArg is in the internal package, so it can not be used outside of this package directly, | ||||
| // it makes sure that user-provided arguments won't cause RCE risks. | ||||
| // User-provided arguments should be passed by other AddXxx functions | ||||
| func (c *Command) AddArguments(args ...internal.CmdArg) *Command { | ||||
| 	for _, arg := range args { | ||||
| 		c.args = append(c.args, string(arg)) | ||||
| 	} | ||||
| 	return c | ||||
| } | ||||
|  | ||||
| // AddDynamicArguments adds new dynamic argument(s) to the command. | ||||
| // The arguments may come from user input and can not be trusted, so no leading '-' is allowed to avoid passing options | ||||
| // AddOptionValues adds a new option with a list of non-option values | ||||
| // For example: AddOptionValues("--opt", val) means 2 arguments: {"--opt", val}. | ||||
| // The values are treated as dynamic argument values. It equals to: AddArguments("--opt") then AddDynamicArguments(val). | ||||
| func (c *Command) AddOptionValues(opt internal.CmdArg, args ...string) *Command { | ||||
| 	if !isValidArgumentOption(string(opt)) { | ||||
| 		c.brokenArgs = append(c.brokenArgs, string(opt)) | ||||
| 		return c | ||||
| 	} | ||||
| 	c.args = append(c.args, string(opt)) | ||||
| 	c.AddDynamicArguments(args...) | ||||
| 	return c | ||||
| } | ||||
|  | ||||
| // AddOptionFormat adds a new option with a format string and arguments | ||||
| // For example: AddOptionFormat("--opt=%s %s", val1, val2) means 1 argument: {"--opt=val1 val2"}. | ||||
| func (c *Command) AddOptionFormat(opt string, args ...any) *Command { | ||||
| 	if !isValidArgumentOption(opt) { | ||||
| 		c.brokenArgs = append(c.brokenArgs, opt) | ||||
| 		return c | ||||
| 	} | ||||
| 	// a quick check to make sure the format string matches the number of arguments, to find low-level mistakes ASAP | ||||
| 	if strings.Count(strings.ReplaceAll(opt, "%%", ""), "%") != len(args) { | ||||
| 		c.brokenArgs = append(c.brokenArgs, opt) | ||||
| 		return c | ||||
| 	} | ||||
| 	s := fmt.Sprintf(opt, args...) | ||||
| 	c.args = append(c.args, s) | ||||
| 	return c | ||||
| } | ||||
|  | ||||
| // AddDynamicArguments adds new dynamic argument values to the command. | ||||
| // The arguments may come from user input and can not be trusted, so no leading '-' is allowed to avoid passing options. | ||||
| // TODO: in the future, this function can be renamed to AddArgumentValues | ||||
| func (c *Command) AddDynamicArguments(args ...string) *Command { | ||||
| 	for _, arg := range args { | ||||
| 		if arg != "" && arg[0] == '-' { | ||||
| 		if !isSafeArgumentValue(arg) { | ||||
| 			c.brokenArgs = append(c.brokenArgs, arg) | ||||
| 		} | ||||
| 	} | ||||
| @@ -137,14 +178,14 @@ func (c *Command) AddDashesAndList(list ...string) *Command { | ||||
| 	return c | ||||
| } | ||||
|  | ||||
| // CmdArgCheck checks whether the string is safe to be used as a dynamic argument. | ||||
| // It panics if the check fails. Usually it should not be used, it's just for refactoring purpose | ||||
| // deprecated | ||||
| func CmdArgCheck(s string) CmdArg { | ||||
| 	if s != "" && s[0] == '-' { | ||||
| 		panic("invalid git cmd argument: " + s) | ||||
| // ToTrustedCmdArgs converts a list of strings (trusted as argument) to TrustedCmdArgs | ||||
| // In most cases, it shouldn't be used. Use AddXxx function instead | ||||
| func ToTrustedCmdArgs(args []string) TrustedCmdArgs { | ||||
| 	ret := make(TrustedCmdArgs, len(args)) | ||||
| 	for i, arg := range args { | ||||
| 		ret[i] = internal.CmdArg(arg) | ||||
| 	} | ||||
| 	return CmdArg(s) | ||||
| 	return ret | ||||
| } | ||||
|  | ||||
| // RunOpts represents parameters to run the command. If UseContextTimeout is specified, then Timeout is ignored. | ||||
| @@ -364,9 +405,9 @@ func (c *Command) RunStdBytes(opts *RunOpts) (stdout, stderr []byte, runErr RunS | ||||
| } | ||||
|  | ||||
| // AllowLFSFiltersArgs return globalCommandArgs with lfs filter, it should only be used for tests | ||||
| func AllowLFSFiltersArgs() []CmdArg { | ||||
| func AllowLFSFiltersArgs() TrustedCmdArgs { | ||||
| 	// Now here we should explicitly allow lfs filters to run | ||||
| 	filteredLFSGlobalArgs := make([]CmdArg, len(globalCommandArgs)) | ||||
| 	filteredLFSGlobalArgs := make(TrustedCmdArgs, len(globalCommandArgs)) | ||||
| 	j := 0 | ||||
| 	for _, arg := range globalCommandArgs { | ||||
| 		if strings.Contains(string(arg), "lfs") { | ||||
|   | ||||
		Reference in New Issue
	
	Block a user